├── lue ├── py.typed ├── tts │ ├── __init__.py │ ├── edge_tts.py │ ├── base.py │ └── kokoro_tts.py ├── __init__.py ├── keys_default.json ├── keys_vim.json ├── config.py ├── guide.txt ├── tts_manager.py ├── progress_manager.py ├── input_handler.py ├── __main__.py ├── audio.py └── timing_calculator.py ├── images ├── lue-icon.png └── lue-screenshot.gif ├── MANIFEST.in ├── requirements.txt ├── pyproject.toml ├── .gitignore ├── README.md ├── DEVELOPER.md ├── VOICES.md └── LICENSE /lue/py.typed: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /images/lue-icon.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/superstarryeyes/lue/HEAD/images/lue-icon.png -------------------------------------------------------------------------------- /images/lue-screenshot.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/superstarryeyes/lue/HEAD/images/lue-screenshot.gif -------------------------------------------------------------------------------- /lue/tts/__init__.py: -------------------------------------------------------------------------------- 1 | """Text-to-speech models for the Lue eBook reader.""" 2 | 3 | from .base import TTSBase 4 | 5 | __all__ = ['TTSBase'] -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- 1 | include README.md 2 | include LICENSE 3 | include requirements.txt 4 | include DEVELOPER.md 5 | include VOICES.md 6 | recursive-include lue *.py 7 | recursive-include lue *.typed 8 | recursive-include lue *.txt 9 | recursive-include lue *.json -------------------------------------------------------------------------------- /lue/__init__.py: -------------------------------------------------------------------------------- 1 | """ 2 | Lue - Terminal eBook Reader with Text-to-Speech 3 | 4 | Multi-format support for EPUB, PDF, TXT, DOCX, HTML, RTF, and Markdown 5 | with modular TTS system featuring Edge TTS (default) and Kokoro TTS (local/offline). 6 | Rich terminal UI with smart persistence and cross-platform support. 7 | """ 8 | 9 | __version__ = "0.4.0" 10 | __author__ = "Starry Eyes" -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | # Core dependencies 2 | python-docx>=1.2.0 3 | striprtf>=0.0.29 4 | rich>=14.1.0 5 | PyMuPDF>=1.26.3 6 | Markdown>=3.8.2 7 | platformdirs>=4.3.8 8 | 9 | # Default TTS model 10 | edge-tts>=7.2.7 11 | 12 | ## Optional TTS models (uncomment to enable) 13 | ## For Kokoro TTS, also install PyTorch for your platform: 14 | ## CPU: pip install torch torchvision torchaudio 15 | ## CUDA: pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121 16 | # kokoro>=0.9.4 17 | # soundfile>=0.13.1 18 | # huggingface-hub>=0.34.4 -------------------------------------------------------------------------------- /lue/keys_default.json: -------------------------------------------------------------------------------- 1 | { 2 | "navigation": { 3 | "next_paragraph": "l", 4 | "prev_paragraph": "h", 5 | "next_sentence": "k", 6 | "prev_sentence": "j", 7 | "scroll_page_up": "i", 8 | "scroll_page_down": "m", 9 | "scroll_up": "u", 10 | "scroll_down": "n", 11 | "move_to_top_visible": "t", 12 | "move_to_beginning": "y", 13 | "move_to_end": "b" 14 | }, 15 | "tts_controls": { 16 | "play_pause": "p", 17 | "decrease_speed": ",", 18 | "increase_speed": ".", 19 | "toggle_sentence_highlight": "s", 20 | "toggle_word_highlight": "w" 21 | }, 22 | "display_controls": { 23 | "toggle_auto_scroll": "a", 24 | "cycle_ui_complexity": "v" 25 | }, 26 | "application": { 27 | "quit": "q", 28 | "toggle_recent_menu": "r", 29 | "select_menu_item": "\n" 30 | } 31 | } -------------------------------------------------------------------------------- /lue/keys_vim.json: -------------------------------------------------------------------------------- 1 | { 2 | "navigation": { 3 | "next_paragraph": "j", 4 | "prev_paragraph": "k", 5 | "next_sentence": ")", 6 | "prev_sentence": "(", 7 | "scroll_page_up": "\u0002", 8 | "scroll_page_down": "\u0006", 9 | "scroll_up": "\u0015", 10 | "scroll_down": "\u0004", 11 | "move_to_top_visible": "H", 12 | "move_to_beginning": "g", 13 | "move_to_end": "G" 14 | }, 15 | "tts_controls": { 16 | "play_pause": "p", 17 | "decrease_speed": ",", 18 | "increase_speed": ".", 19 | "toggle_sentence_highlight": "s", 20 | "toggle_word_highlight": "w" 21 | }, 22 | "display_controls": { 23 | "toggle_auto_scroll": "a", 24 | "cycle_ui_complexity": "v" 25 | }, 26 | "application": { 27 | "quit": "q", 28 | "toggle_recent_menu": "r", 29 | "select_menu_item": "\n" 30 | } 31 | } -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- 1 | [build-system] 2 | requires = ["setuptools>=61.0", "wheel"] 3 | build-backend = "setuptools.build_meta" 4 | 5 | [project] 6 | name = "lue-reader" 7 | version = "0.4.0" 8 | description = "A terminal-based eBook reader with modular text-to-speech capabilities and multi-format support" 9 | readme = "README.md" 10 | license = {text = "GPL-3.0-or-later"} 11 | authors = [ 12 | {name = "Starry Eyes"} 13 | ] 14 | classifiers = [ 15 | "Development Status :: 4 - Beta", 16 | "Intended Audience :: End Users/Desktop", 17 | "License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)", 18 | "Operating System :: OS Independent", 19 | "Programming Language :: Python :: 3", 20 | "Programming Language :: Python :: 3.10", 21 | "Programming Language :: Python :: 3.11", 22 | "Programming Language :: Python :: 3.12", 23 | "Topic :: Multimedia :: Sound/Audio :: Speech", 24 | "Topic :: Text Processing", 25 | "Environment :: Console", 26 | ] 27 | requires-python = ">=3.10" 28 | dependencies = [ 29 | "python-docx>=1.2.0", 30 | "striprtf>=0.0.29", 31 | "rich>=14.1.0", 32 | "PyMuPDF>=1.26.3", 33 | "Markdown>=3.8.2", 34 | "platformdirs>=4.3.8", 35 | "edge-tts>=7.2.0", 36 | ] 37 | 38 | [project.optional-dependencies] 39 | kokoro = [ 40 | "kokoro>=0.9.4", 41 | "soundfile>=0.13.1", 42 | "huggingface-hub>=0.34.4", 43 | ] 44 | 45 | [project.scripts] 46 | lue = "lue.__main__:cli" 47 | 48 | [project.urls] 49 | Homepage = "https://github.com/superstarryeyes/lue" 50 | Repository = "https://github.com/superstarryeyes/lue" 51 | Issues = "https://github.com/superstarryeyes/lue/issues" 52 | 53 | [tool.setuptools.packages.find] 54 | include = ["lue*"] 55 | 56 | [tool.setuptools.package-data] 57 | lue = ["py.typed", "guide.txt", "*.json"] -------------------------------------------------------------------------------- /lue/config.py: -------------------------------------------------------------------------------- 1 | """Configuration settings for the Lue eBook reader.""" 2 | 3 | import os 4 | from platformdirs import user_data_dir, user_cache_dir 5 | 6 | # Default TTS model 7 | DEFAULT_TTS_MODEL = "edge" 8 | 9 | # Default voices for TTS models 10 | TTS_VOICES = { 11 | "edge": "en-US-JennyNeural", 12 | "kokoro": "af_heart", 13 | } 14 | 15 | # Language codes for TTS models that require them 16 | TTS_LANGUAGE_CODES = { 17 | "kokoro": "a", # a=English, e=Spanish, j=Japanese, etc. 18 | } 19 | 20 | # TTS model-specific seconds of overlap between sentences (overrides default OVERLAP_SECONDS if specified) 21 | TTS_OVERLAP_SECONDS = { 22 | "kokoro": 0.6, 23 | } 24 | 25 | # Audio processing settings 26 | AUDIO_DATA_DIR = user_cache_dir("lue") 27 | os.makedirs(AUDIO_DATA_DIR, exist_ok=True) 28 | AUDIO_BUFFERS = [os.path.join(AUDIO_DATA_DIR, f"buffer_{i}") for i in range(6)] 29 | MAX_QUEUE_SIZE = 4 30 | OVERLAP_SECONDS = 0.5 # Seconds of overlap between sentences 31 | 32 | # Progress tracking settings 33 | PROGRESS_FILE_DIR = user_data_dir("lue") 34 | os.makedirs(PROGRESS_FILE_DIR, exist_ok=True) 35 | 36 | # General settings 37 | SHOW_ERRORS_ON_EXIT = True 38 | 39 | # PDF parsing settings 40 | PDF_FILTERS_ENABLED = False # You can also enable this with the --filter or -f command-line option 41 | PDF_FILTER_HEADERS = True # Filter headers in top margin of pages 42 | PDF_FILTER_FOOTNOTES = True # Filter page numbers and footnotes in bottom margin of pages 43 | 44 | # PDF filtering thresholds (only used when respective filters are enabled) 45 | PDF_HEADER_MARGIN = 0.1 # Top 10% of page considered header area 46 | PDF_FOOTNOTE_MARGIN = 0.1 # Bottom 10% of page considered footnote area 47 | 48 | # UI settings 49 | SMOOTH_SCROLLING_ENABLED = True # Enable smooth scrolling for keyboard navigation 50 | UI_COMPLEXITY_MODE = 2 # 0=minimal (text only), 1=medium (top bar only), 2=full (default) 51 | 52 | # Highlighting settings 53 | SENTENCE_HIGHLIGHTING_ENABLED = True # Enable sentence-level highlighting 54 | WORD_HIGHLIGHT_MODE = 1 # 0=off, 1=normal highlighting, 2=standout highlighting 55 | 56 | # Keyboard settings 57 | # Can be set to "default", "vim", or a path to a custom keyboard shortcuts JSON file 58 | CUSTOM_KEYBOARD_SHORTCUTS = "default" 59 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # Distribution / packaging 7 | .Python 8 | build/ 9 | develop-eggs/ 10 | dist/ 11 | downloads/ 12 | eggs/ 13 | .eggs/ 14 | lib/ 15 | lib64/ 16 | parts/ 17 | sdist/ 18 | var/ 19 | wheels/ 20 | pip-wheel-metadata/ 21 | share/python-wheels/ 22 | *.egg-info/ 23 | .installed.cfg 24 | *.egg 25 | MANIFEST 26 | 27 | # PyInstaller 28 | *.spec 29 | 30 | # Installer logs 31 | pip-log.txt 32 | pip-delete-this-directory.txt 33 | 34 | # Unit test / coverage reports 35 | htmlcov/ 36 | .tox/ 37 | .nox/ 38 | .coverage 39 | .coverage.* 40 | .cache 41 | nosetests.xml 42 | coverage.xml 43 | *.cover 44 | *.py,cover 45 | .hypothesis/ 46 | .pytest_cache/ 47 | cover/ 48 | 49 | # Translations 50 | *.mo 51 | *.pot 52 | 53 | # Django stuff: 54 | *.log 55 | local_settings.py 56 | db.sqlite3 57 | db.sqlite3-journal 58 | 59 | # Flask stuff: 60 | instance/ 61 | .webassets-cache 62 | 63 | # Scrapy stuff: 64 | .scrapy 65 | 66 | # Sphinx documentation 67 | docs/_build/ 68 | 69 | # PyBuilder 70 | .pybuilder/ 71 | target/ 72 | 73 | # Jupyter Notebook 74 | .ipynb_checkpoints 75 | 76 | # IPython 77 | profile_default/ 78 | ipython_config.py 79 | 80 | # pyenv 81 | .python-version 82 | 83 | # pipenv 84 | Pipfile.lock 85 | 86 | # poetry 87 | poetry.lock 88 | 89 | # pdm 90 | .pdm.toml 91 | 92 | # PEP 582 93 | __pypackages__/ 94 | 95 | # Celery stuff 96 | celerybeat-schedule 97 | celerybeat.pid 98 | 99 | # SageMath parsed files 100 | *.sage.py 101 | 102 | # Environments 103 | .env 104 | .venv 105 | env/ 106 | venv/ 107 | ENV/ 108 | env.bak/ 109 | venv.bak/ 110 | 111 | # Spyder project settings 112 | .spyderproject 113 | .spyproject 114 | 115 | # Rope project settings 116 | .ropeproject 117 | 118 | # mkdocs documentation 119 | /site 120 | 121 | # mypy 122 | .mypy_cache/ 123 | .dmypy.json 124 | dmypy.json 125 | 126 | # Pyre type checker 127 | .pyre/ 128 | 129 | # pytype static type analyzer 130 | .pytype/ 131 | 132 | # Cython debug symbols 133 | cython_debug/ 134 | 135 | # PyCharm 136 | .idea/ 137 | 138 | # macOS 139 | .DS_Store 140 | .AppleDouble 141 | .LSOverride 142 | 143 | # Windows 144 | Thumbs.db 145 | ehthumbs.db 146 | Desktop.ini 147 | 148 | # Linux 149 | *~ 150 | 151 | # Application data 152 | data/ 153 | *.mp3 154 | *.wav 155 | 156 | # IDE 157 | .vscode/ 158 | *.swp 159 | *.swo 160 | 161 | # Logs 162 | *.log 163 | -------------------------------------------------------------------------------- /lue/guide.txt: -------------------------------------------------------------------------------- 1 | Chapter 1: Introduction 2 | 3 | Welcome to Lue, your terminal-based eBook reader with modular text-to-speech support. This document is designed to let you practice navigating your book while hearing instructions read aloud. 4 | 5 | 6 | Chapter 2: Reading Controls 7 | 8 | Now let’s test sentence-level navigation. Press "j" to return to the previous sentence. Press "k" to jump to the next sentence. If you want to jump to the top visible sentence on the screen, press "t" key. Press "h" to go back to the previous paragraph. Press "l" to move to the next paragraph. You can pause and resume the text-to-speech model with "p", Lue remembers exactly where you were. 9 | 10 | 11 | Chapter 3: Page and Scroll Controls 12 | 13 | You can scroll through the book without losing the highlighted sentence being read. Do that by pressing "i" to move page up, and "m" to move page down. For smaller adjustments, use "u" to scroll up or "n" to scroll down a row. Navigating with these keys, the mouse wheel, or a trackpad automatically switches Lue to manual mode. In this mode, pressing "a", returns you back to the highlighted sentence and reactivates auto-scroll mode. Auto-scroll works seamlessly with TTS, keeping your reading flow smooth and uninterrupted. "y" takes you to the beginning, and "b" takes you to the end of the book. 14 | 15 | 16 | Chapter 4: Mouse Actions 17 | 18 | If your terminal supports mouse input, you can click on any sentence to jump to it instantly. Use the mouse wheel or trackpad to scroll through the text, or click on the progress bar to skip directly to that position in the book. 19 | 20 | 21 | Chapter 5: Speed Adjustment 22 | 23 | Lue allows you to adjust the text-to-speech playback speed to match your listening preference. You can increase the speed up to 3x faster. To increase the playback speed, press the period key. Each press will increase the speed incrementally. To decrease the playback speed, press the comma key. Each press will decrease the speed back down to the normal 1x speed. 24 | 25 | 26 | Chapter 6: Highlighting Controls 27 | 28 | There are two levels of text highlighting to help you follow along with the narration: sentence-level highlighting and word-level highlighting. To toggle sentence highlighting on or off, press the "s" key. To toggle word highlighting on or off, press the "w" key. You can use both highlighting modes simultaneously, or disable either one based on your preference. 29 | 30 | 31 | Chapter 7: Ending the Session 32 | 33 | When you are ready to stop reading, press "q" to quit. Your place and your reading mode will be saved automatically, so you can resume later without losing your spot. 34 | 35 | 36 | Enjoy your reading! -------------------------------------------------------------------------------- /lue/tts_manager.py: -------------------------------------------------------------------------------- 1 | """TTS model discovery and management for the Lue eBook reader.""" 2 | 3 | import importlib 4 | import inspect 5 | import logging 6 | from pathlib import Path 7 | from rich.console import Console 8 | from .tts.base import TTSBase 9 | from . import config 10 | 11 | 12 | class TTSManager: 13 | """ 14 | Discovers, loads, and manages available TTS models. 15 | 16 | This class automatically discovers TTS models in the tts/ directory 17 | and provides a unified interface for creating model instances. 18 | """ 19 | 20 | def __init__(self): 21 | """Initialize the TTS manager and discover available models.""" 22 | self._models = {} 23 | self._discover_models() 24 | 25 | def _discover_models(self): 26 | """ 27 | Dynamically discover TTS models from the tts/ directory. 28 | 29 | Looks for Python files matching the pattern '*_tts.py' and attempts 30 | to load classes that inherit from TTSBase. 31 | """ 32 | tts_dir = Path(__file__).parent / "tts" 33 | for file_path in tts_dir.glob("*_tts.py"): 34 | module_name = file_path.stem 35 | try: 36 | module = importlib.import_module(f".tts.{module_name}", package="lue") 37 | for name, obj in inspect.getmembers(module, inspect.isclass): 38 | if (issubclass(obj, TTSBase) and 39 | not inspect.isabstract(obj) and 40 | obj is not TTSBase): 41 | model_name = module_name.replace("_tts", "") 42 | self._models[model_name] = obj 43 | logging.info(f"Discovered TTS model: {model_name}") 44 | break 45 | except Exception as e: 46 | logging.error(f"Failed to load TTS module {module_name}: {e}", exc_info=True) 47 | 48 | def get_available_tts_names(self) -> list[str]: 49 | """ 50 | Get a list of available TTS model names. 51 | 52 | Returns: 53 | list[str]: Sorted list of model names, with the default model first. 54 | """ 55 | names = sorted(self._models.keys()) 56 | # Prioritize the default TTS model 57 | default_model = get_default_tts_model_name(names) 58 | if default_model in names: 59 | names.remove(default_model) 60 | names.insert(0, default_model) 61 | return names 62 | 63 | def create_model(self, name: str, console: Console, voice: str = None, lang: str = None) -> TTSBase | None: 64 | """ 65 | Create an instance of the specified TTS model. 66 | 67 | Args: 68 | name: Name of the TTS model to create 69 | console: Rich console instance for user feedback 70 | voice: Optional voice for the TTS model 71 | lang: Optional language for the TTS model 72 | 73 | Returns: 74 | TTSBase: Model instance, or None if model not found 75 | """ 76 | model_class = self._models.get(name) 77 | if model_class: 78 | return model_class(console, voice=voice, lang=lang) 79 | logging.error(f"TTS model '{name}' not found.") 80 | return None 81 | 82 | 83 | def get_default_tts_model_name(available_models: list[str]) -> str: 84 | """ 85 | Determine the default TTS model name from the available list. 86 | 87 | Uses the model specified in config.py, falling back to the first available 88 | model if the configured one is not found. 89 | 90 | Args: 91 | available_models: List of available model names 92 | 93 | Returns: 94 | str: Name of the default TTS model 95 | """ 96 | if config.DEFAULT_TTS_MODEL in available_models: 97 | return config.DEFAULT_TTS_MODEL 98 | return available_models[0] if available_models else "" -------------------------------------------------------------------------------- /lue/tts/edge_tts.py: -------------------------------------------------------------------------------- 1 | import os 2 | import asyncio 3 | import logging 4 | from rich.console import Console 5 | 6 | from .base import TTSBase 7 | from .. import config 8 | 9 | class EdgeTTS(TTSBase): 10 | """TTS implementation for Microsoft Edge's online TTS service.""" 11 | 12 | @property 13 | def name(self) -> str: 14 | return "edge" 15 | 16 | @property 17 | def output_format(self) -> str: 18 | return "mp3" 19 | 20 | def __init__(self, console: Console, voice: str = None, lang: str = None): 21 | super().__init__(console, voice, lang) 22 | self.edge_tts = None 23 | if self.voice is None: 24 | self.voice = config.TTS_VOICES.get(self.name) 25 | 26 | async def initialize(self) -> bool: 27 | """Checks if the edge-tts library is available.""" 28 | try: 29 | import edge_tts 30 | self.edge_tts = edge_tts 31 | self.initialized = True 32 | self.console.print("[green]Edge TTS model is available.[/green]") 33 | return True 34 | except ImportError: 35 | self.console.print("[bold red]Error: 'edge-tts' package not found.[/bold red]") 36 | self.console.print("[yellow]Please run 'pip install edge-tts' to use this TTS model.[/yellow]") 37 | logging.error("'edge-tts' is not installed.") 38 | return False 39 | 40 | async def get_raw_timing_data(self, text: str, output_path: str): 41 | """ 42 | Get raw word timing data from Edge TTS. 43 | 44 | Returns: 45 | List of (word, start_time, end_time) tuples with raw timing data from Edge TTS 46 | """ 47 | if not self.initialized: 48 | raise RuntimeError("Edge TTS has not been initialized.") 49 | 50 | try: 51 | communicate = self.edge_tts.Communicate(text, self.voice, boundary="WordBoundary") 52 | 53 | # Collect word timing information 54 | word_timings = [] 55 | audio_chunks = [] 56 | 57 | async for chunk in communicate.stream(): 58 | if chunk['type'] == 'WordBoundary': 59 | # Convert from 100-nanosecond units to seconds 60 | start_time = chunk['offset'] / 10000000.0 61 | end_time = (chunk['offset'] + chunk['duration']) / 10000000.0 62 | word_timings.append((chunk['text'], start_time, end_time)) 63 | elif chunk['type'] == 'audio': 64 | audio_chunks.append(chunk['data']) 65 | 66 | # Save audio to file 67 | with open(output_path, 'wb') as f: 68 | for chunk in audio_chunks: 69 | f.write(chunk) 70 | 71 | return word_timings 72 | 73 | except Exception as e: 74 | logging.error(f"Edge TTS audio generation failed for text: '{text[:50]}...'", exc_info=True) 75 | raise e 76 | 77 | async def generate_audio_with_timing(self, text: str, output_path: str): 78 | """ 79 | Generate audio with timing using the centralized timing calculator. 80 | 81 | This method leverages Edge TTS's precise word boundary information 82 | through get_raw_timing_data() and processes it with the timing calculator. 83 | """ 84 | # Get raw timing data (which also generates the audio) 85 | raw_timings = await self.get_raw_timing_data(text, output_path) 86 | 87 | # Get actual audio duration 88 | try: 89 | from .. import audio 90 | except ImportError: 91 | import sys 92 | import os 93 | sys.path.insert(0, os.path.dirname(os.path.dirname(__file__))) 94 | import audio 95 | duration = await audio.get_audio_duration(output_path) 96 | 97 | # Process timing data using the centralized calculator 98 | try: 99 | from ..timing_calculator import process_tts_timing_data 100 | except ImportError: 101 | import sys 102 | import os 103 | sys.path.insert(0, os.path.dirname(os.path.dirname(__file__))) 104 | import timing_calculator 105 | process_tts_timing_data = timing_calculator.process_tts_timing_data 106 | return process_tts_timing_data(text, raw_timings, duration) 107 | 108 | async def generate_audio(self, text: str, output_path: str): 109 | """Generates audio from text using edge-tts and saves it to a file.""" 110 | if not self.initialized: 111 | raise RuntimeError("Edge TTS has not been initialized.") 112 | try: 113 | communicate = self.edge_tts.Communicate(text, self.voice) 114 | await communicate.save(output_path) 115 | except Exception as e: 116 | logging.error(f"Edge TTS audio generation failed for text: '{text[:50]}...'", exc_info=True) 117 | raise e 118 | 119 | async def warm_up(self): 120 | """Warms up the TTS model by making a short request.""" 121 | if not self.initialized: 122 | return 123 | 124 | self.console.print("[bold cyan]Warming up the Edge TTS model...[/bold cyan]") 125 | warmup_file = os.path.join(config.AUDIO_DATA_DIR, f".warmup_edge.{self.output_format}") 126 | try: 127 | await self.generate_audio("Ready.", warmup_file) 128 | self.console.print("[green]Edge TTS model is ready.[/green]") 129 | except Exception as e: 130 | self.console.print(f"[bold yellow]Warning: Edge model warm-up failed.[/bold yellow]") 131 | self.console.print(f"[yellow]This may indicate a network issue or an invalid voice name: {self.voice}[/yellow]") 132 | logging.warning(f"Edge TTS model warm-up failed: {e}", exc_info=True) 133 | finally: 134 | if os.path.exists(warmup_file): 135 | try: 136 | os.remove(warmup_file) 137 | except OSError: 138 | pass -------------------------------------------------------------------------------- /lue/tts/base.py: -------------------------------------------------------------------------------- 1 | """Abstract base class for TTS models in the Lue eBook reader.""" 2 | 3 | from abc import ABC, abstractmethod 4 | from rich.console import Console 5 | 6 | 7 | class TTSBase(ABC): 8 | """ 9 | Abstract base class for all TTS models. 10 | 11 | This class defines the interface that all TTS models must implement 12 | to be compatible with the Lue eBook reader. 13 | """ 14 | 15 | def __init__(self, console: Console, voice: str = None, lang: str = None): 16 | """ 17 | Initialize the TTS model. 18 | 19 | Args: 20 | console: Rich console instance for user feedback 21 | voice: Optional voice for the TTS model 22 | lang: Optional language for the TTS model 23 | """ 24 | self.console = console 25 | self.voice = voice 26 | self.lang = lang 27 | self.initialized = False 28 | 29 | @property 30 | @abstractmethod 31 | def name(self) -> str: 32 | """ 33 | Get the unique identifier for this TTS model. 34 | 35 | Returns: 36 | str: Model name (e.g., 'edge', 'kokoro') 37 | """ 38 | pass 39 | 40 | @property 41 | @abstractmethod 42 | def output_format(self) -> str: 43 | """ 44 | Get the audio format this model produces. 45 | 46 | Returns: 47 | str: File extension without dot (e.g., 'mp3', 'wav') 48 | """ 49 | pass 50 | 51 | @abstractmethod 52 | async def initialize(self) -> bool: 53 | """ 54 | Initialize the TTS model asynchronously. 55 | 56 | This method should: 57 | - Check for required dependencies 58 | - Load models if necessary 59 | - Handle ImportErrors gracefully 60 | - Set self.initialized = True on success 61 | 62 | Returns: 63 | bool: True if initialization succeeded, False otherwise 64 | """ 65 | pass 66 | 67 | @abstractmethod 68 | async def generate_audio(self, text: str, output_path: str): 69 | """ 70 | Generate audio from text and save to file. 71 | 72 | Args: 73 | text: Text to convert to speech 74 | output_path: Full path where audio file should be saved 75 | 76 | Raises: 77 | RuntimeError: If model is not initialized 78 | Exception: If audio generation fails 79 | """ 80 | pass 81 | 82 | async def generate_audio_with_timing(self, text: str, output_path: str): 83 | """ 84 | Generate audio from text and save to file, returning processed timing information. 85 | 86 | This method now uses the centralized timing calculator to process timing data. 87 | TTS implementations should override get_raw_timing_data() to provide engine-specific 88 | timing information, while this method handles all the processing and adjustments. 89 | 90 | Args: 91 | text: Text to convert to speech 92 | output_path: Full path where audio file should be saved 93 | 94 | Returns: 95 | dict: Processed timing information containing: 96 | - word_timings: List of (word, start_time, end_time) tuples 97 | - speech_duration: Duration of speech content 98 | - total_duration: Total audio duration 99 | - word_mapping: Mapping from original words to TTS timings 100 | 101 | Raises: 102 | RuntimeError: If model is not initialized 103 | Exception: If audio generation fails 104 | """ 105 | # Generate audio first 106 | await self.generate_audio(text, output_path) 107 | 108 | # Get raw timing data from the TTS implementation 109 | raw_timings = await self.get_raw_timing_data(text, output_path) 110 | 111 | # Get actual audio duration 112 | try: 113 | from .. import audio 114 | except ImportError: 115 | # Handle case when running tests or imports from different context 116 | import sys 117 | import os 118 | sys.path.insert(0, os.path.dirname(os.path.dirname(__file__))) 119 | import audio 120 | duration = await audio.get_audio_duration(output_path) 121 | 122 | # Process timing data using the centralized calculator 123 | try: 124 | from ..timing_calculator import process_tts_timing_data 125 | except ImportError: 126 | # Handle case when running tests or imports from different context 127 | import sys 128 | import os 129 | sys.path.insert(0, os.path.dirname(os.path.dirname(__file__))) 130 | import timing_calculator 131 | process_tts_timing_data = timing_calculator.process_tts_timing_data 132 | return process_tts_timing_data(text, raw_timings, duration) 133 | 134 | async def get_raw_timing_data(self, text: str, output_path: str): 135 | """ 136 | Get raw timing data from the TTS engine. 137 | 138 | This method should be overridden by TTS implementations that can provide 139 | precise timing information. The default implementation returns empty list, 140 | which will cause the timing calculator to estimate timings. 141 | 142 | Args: 143 | text: Text that was converted to speech 144 | output_path: Path to the generated audio file 145 | 146 | Returns: 147 | List of (word, start_time, end_time) tuples with raw timing data from TTS engine, 148 | or empty list if no timing data is available 149 | """ 150 | return [] 151 | 152 | async def warm_up(self): 153 | """ 154 | Warm up the model to reduce initial latency. 155 | 156 | This is called once after initialization to prepare the model 157 | for faster subsequent audio generation. 158 | """ 159 | pass 160 | 161 | def get_overlap_seconds(self) -> float | None: 162 | """ 163 | Get the TTS-specific overlap seconds for this model. 164 | 165 | Returns: 166 | float: Overlap seconds specific to this TTS model, or None to use default 167 | """ 168 | from .. import config 169 | return config.TTS_OVERLAP_SECONDS.get(self.name) -------------------------------------------------------------------------------- /lue/progress_manager.py: -------------------------------------------------------------------------------- 1 | """Reading progress management for the Lue eBook reader.""" 2 | 3 | import os 4 | import json 5 | import re 6 | import glob 7 | from . import config 8 | 9 | 10 | def get_progress_file_path(book_title): 11 | """ 12 | Generate the file path for storing reading progress. 13 | 14 | Args: 15 | book_title: Title of the book 16 | 17 | Returns: 18 | str: Full path to the progress file 19 | """ 20 | safe_title = re.sub(r'[^A-Za-z0-9]+', '', book_title) 21 | return os.path.join(config.PROGRESS_FILE_DIR, f"{safe_title}.progress.json") 22 | 23 | def load_progress(progress_file): 24 | """ 25 | Load basic reading progress from file. 26 | 27 | Args: 28 | progress_file: Path to the progress file 29 | 30 | Returns: 31 | tuple: (chapter_idx, paragraph_idx, sentence_idx) 32 | """ 33 | if os.path.exists(progress_file): 34 | with open(progress_file, 'r', encoding='utf-8') as f: 35 | try: 36 | data = json.load(f) 37 | return data.get("c", 0), data.get("p", 0), data.get("s", 0) 38 | except json.JSONDecodeError: 39 | return 0, 0, 0 40 | return 0, 0, 0 41 | 42 | def load_extended_progress(progress_file): 43 | """ 44 | Load extended reading progress including UI state. 45 | 46 | Args: 47 | progress_file: Path to the progress file 48 | 49 | Returns: 50 | dict: Progress data with reading position and UI state 51 | """ 52 | default_progress = { 53 | "c": 0, "p": 0, "s": 0, 54 | "scroll_offset": 0, 55 | "tts_enabled": True, 56 | "auto_scroll_enabled": True, 57 | "manual_scroll_anchor": None, 58 | "playback_speed": 1.0 59 | } 60 | 61 | if not os.path.exists(progress_file): 62 | return default_progress 63 | 64 | try: 65 | with open(progress_file, 'r', encoding='utf-8') as f: 66 | data = json.load(f) 67 | return { 68 | "c": data.get("c", 0), 69 | "p": data.get("p", 0), 70 | "s": data.get("s", 0), 71 | "scroll_offset": data.get("scroll_offset", 0), 72 | "tts_enabled": data.get("tts_enabled", True), 73 | "auto_scroll_enabled": data.get("auto_scroll_enabled", True), 74 | "manual_scroll_anchor": data.get("manual_scroll_anchor", None), 75 | "playback_speed": data.get("playback_speed", 1.0) 76 | } 77 | except (json.JSONDecodeError, IOError): 78 | return default_progress 79 | 80 | def save_progress(progress_file, chapter_idx, paragraph_idx, sentence_idx): 81 | """ 82 | Save basic reading progress to file. 83 | 84 | Args: 85 | progress_file: Path to the progress file 86 | chapter_idx: Current chapter index 87 | paragraph_idx: Current paragraph index 88 | sentence_idx: Current sentence index 89 | """ 90 | progress = {"c": chapter_idx, "p": paragraph_idx, "s": sentence_idx} 91 | with open(progress_file, 'w', encoding='utf-8') as f: 92 | json.dump(progress, f, indent=2) 93 | 94 | def save_extended_progress(progress_file, chapter_idx, paragraph_idx, sentence_idx, 95 | scroll_offset, tts_enabled, auto_scroll_enabled, manual_scroll_anchor=None, original_file_path=None, playback_speed=1.0, percentage=0.0): 96 | """ 97 | Save extended reading progress including UI state. 98 | 99 | Args: 100 | progress_file: Path to the progress file 101 | chapter_idx: Current chapter index 102 | paragraph_idx: Current paragraph index 103 | sentence_idx: Current sentence index 104 | scroll_offset: Current scroll position 105 | tts_enabled: Whether TTS is enabled 106 | auto_scroll_enabled: Whether auto-scroll is enabled 107 | manual_scroll_anchor: Manual scroll anchor position (optional) 108 | original_file_path: Original path to the eBook file (optional) 109 | playback_speed: Audio playback speed 110 | percentage: Completion percentage (0.0 to 100.0) 111 | """ 112 | progress = { 113 | "c": chapter_idx, 114 | "p": paragraph_idx, 115 | "s": sentence_idx, 116 | "scroll_offset": float(scroll_offset), 117 | "tts_enabled": bool(tts_enabled), 118 | "auto_scroll_enabled": bool(auto_scroll_enabled), 119 | "playback_speed": float(playback_speed), 120 | "completion_percentage": float(percentage) 121 | } 122 | if manual_scroll_anchor: 123 | progress["manual_scroll_anchor"] = manual_scroll_anchor 124 | if original_file_path: 125 | progress["original_file_path"] = original_file_path 126 | 127 | # Save percentage if provided (default to 0.0 if not in args, but we will add it to args) 128 | # Note: The function signature will be updated in the next step to include percentage. 129 | # For now, we'll just add it if passed in kwargs or update the signature. 130 | # Actually, I should update the signature in the same edit. 131 | 132 | with open(progress_file, 'w', encoding='utf-8') as f: 133 | json.dump(progress, f, indent=2) 134 | 135 | def get_recent_books(limit=5): 136 | """ 137 | Get a list of recently read books. 138 | 139 | Args: 140 | limit: Maximum number of books to return 141 | 142 | Returns: 143 | list: List of dicts containing title, path, and percentage 144 | """ 145 | progress_files = glob.glob(os.path.join(config.PROGRESS_FILE_DIR, "*.progress.json")) 146 | 147 | # Sort by modification time (newest first) 148 | progress_files.sort(key=os.path.getmtime, reverse=True) 149 | 150 | recent_books = [] 151 | for pf in progress_files: 152 | if len(recent_books) >= limit: 153 | break 154 | 155 | try: 156 | with open(pf, 'r', encoding='utf-8') as f: 157 | data = json.load(f) 158 | 159 | original_path = data.get("original_file_path") 160 | if not original_path or not os.path.exists(original_path): 161 | continue 162 | 163 | # Derive title from filename if not stored (we don't store title currently, so use filename) 164 | title = os.path.basename(original_path) 165 | # Remove extension 166 | title = os.path.splitext(title)[0] 167 | 168 | percentage = data.get("completion_percentage", 0.0) 169 | 170 | recent_books.append({ 171 | "title": title, 172 | "path": original_path, 173 | "percentage": percentage 174 | }) 175 | 176 | except (json.JSONDecodeError, IOError): 177 | continue 178 | 179 | return recent_books 180 | 181 | def validate_and_set_progress(chapters, progress_file, c, p, s): 182 | """ 183 | Validate reading progress against document structure. 184 | 185 | Args: 186 | chapters: Document chapters structure 187 | progress_file: Path to progress file (for cleanup if invalid) 188 | c: Chapter index to validate 189 | p: Paragraph index to validate 190 | s: Sentence index to validate 191 | 192 | Returns: 193 | tuple: Valid (chapter_idx, paragraph_idx, sentence_idx) 194 | """ 195 | try: 196 | paragraph = chapters[c][p] 197 | sentences = re.split(r'(?<=[.!?])\s+', paragraph) 198 | _ = sentences[s] # Test if sentence exists 199 | return c, p, s 200 | except IndexError: 201 | # Invalid progress, reset to beginning 202 | if os.path.exists(progress_file): 203 | os.remove(progress_file) 204 | return 0, 0, 0 205 | 206 | def find_most_recent_book(): 207 | """ 208 | Find the most recently updated progress file and return the original file path. 209 | 210 | Returns: 211 | str or None: Path to the most recently read book, or None if no books found 212 | """ 213 | progress_files = glob.glob(os.path.join(config.PROGRESS_FILE_DIR, "*.progress.json")) 214 | 215 | if not progress_files: 216 | return None 217 | 218 | # Find the most recently modified progress file 219 | most_recent_file = max(progress_files, key=os.path.getmtime) 220 | 221 | try: 222 | with open(most_recent_file, 'r', encoding='utf-8') as f: 223 | data = json.load(f) 224 | original_path = data.get("original_file_path") 225 | 226 | # Check if the original file still exists 227 | if original_path and os.path.exists(original_path): 228 | return original_path 229 | 230 | except (json.JSONDecodeError, IOError): 231 | pass 232 | 233 | return None -------------------------------------------------------------------------------- /lue/input_handler.py: -------------------------------------------------------------------------------- 1 | import sys 2 | import select 3 | import asyncio 4 | import subprocess 5 | import json 6 | import os 7 | 8 | # Default keyboard shortcuts 9 | DEFAULT_KEYBOARD_SHORTCUTS = { 10 | "navigation": { 11 | "next_paragraph": "l", 12 | "prev_paragraph": "h", 13 | "next_sentence": "k", 14 | "prev_sentence": "j", 15 | "scroll_page_up": "i", 16 | "scroll_page_down": "m", 17 | "scroll_up": "u", 18 | "scroll_down": "n", 19 | "move_to_top_visible": "t", 20 | "move_to_beginning": "y", 21 | "move_to_end": "b" 22 | }, 23 | "tts_controls": { 24 | "play_pause": "p", 25 | "decrease_speed": ",", 26 | "increase_speed": ".", 27 | "toggle_sentence_highlight": "s", 28 | "toggle_word_highlight": "w" 29 | }, 30 | "display_controls": { 31 | "toggle_auto_scroll": "a", 32 | "cycle_ui_complexity": "v" 33 | }, 34 | "application": { 35 | "quit": "q" 36 | } 37 | } 38 | 39 | # Global variable to store loaded keyboard shortcuts 40 | KEYBOARD_SHORTCUTS = DEFAULT_KEYBOARD_SHORTCUTS 41 | 42 | def load_keyboard_shortcuts(file_path=None): 43 | """Load keyboard shortcuts from a JSON file or use defaults. 44 | 45 | If file_path is None, the function will attempt to load from the default locations. 46 | """ 47 | global KEYBOARD_SHORTCUTS 48 | 49 | # If no file path provided, use the default file 50 | if not file_path: 51 | file_path = os.path.join(os.path.dirname(__file__), 'keys_default.json') 52 | 53 | try: 54 | with open(file_path, 'r') as f: 55 | KEYBOARD_SHORTCUTS = json.load(f) 56 | except Exception: 57 | # Fallback to default shortcuts if file cannot be loaded 58 | KEYBOARD_SHORTCUTS = DEFAULT_KEYBOARD_SHORTCUTS 59 | 60 | def process_input(reader): 61 | """Process user input from stdin.""" 62 | try: 63 | if select.select([sys.stdin], [], [], 0)[0]: 64 | data = sys.stdin.read(1) 65 | 66 | if not data: 67 | return 68 | 69 | if data == '\x1b': 70 | reader.mouse_sequence_buffer = data 71 | reader.mouse_sequence_active = True 72 | return 73 | elif reader.mouse_sequence_active: 74 | reader.mouse_sequence_buffer += data 75 | 76 | if reader.mouse_sequence_buffer.startswith('\x1b[<') and (data == 'M' or data == 'm'): 77 | sequence = reader.mouse_sequence_buffer 78 | reader.mouse_sequence_buffer = '' 79 | reader.mouse_sequence_active = False 80 | 81 | if len(sequence) > 3: 82 | mouse_part = sequence[3:] 83 | if mouse_part.endswith('M') or mouse_part.endswith('m'): 84 | try: 85 | parts = mouse_part[:-1].split(';') 86 | if len(parts) >= 3: 87 | button = int(parts[0]) 88 | x_pos = int(parts[1]) 89 | y_pos = int(parts[2]) 90 | 91 | if mouse_part.endswith('M'): 92 | if button == 0: 93 | if reader._is_click_on_progress_bar(x_pos, y_pos): 94 | if reader._handle_progress_bar_click(x_pos, y_pos): 95 | return 96 | 97 | if not reader._is_click_on_text(x_pos, y_pos): 98 | return 99 | 100 | # Cancel any pending restart task before killing audio 101 | if hasattr(reader, 'pending_restart_task') and reader.pending_restart_task and not reader.pending_restart_task.done(): 102 | reader.pending_restart_task.cancel() 103 | 104 | _kill_audio_immediately(reader) 105 | reader.loop.call_soon_threadsafe(reader._post_command_sync, ('click_jump', (x_pos, y_pos))) 106 | elif button == 64: 107 | if reader.auto_scroll_enabled: 108 | reader.auto_scroll_enabled = False 109 | reader.loop.call_soon_threadsafe(reader._post_command_sync, 'wheel_scroll_up') 110 | elif button == 65: 111 | if reader.auto_scroll_enabled: 112 | reader.auto_scroll_enabled = False 113 | reader.loop.call_soon_threadsafe(reader._post_command_sync, 'wheel_scroll_down') 114 | return 115 | except (ValueError, IndexError): 116 | pass 117 | return 118 | 119 | elif reader.mouse_sequence_buffer.startswith('\x1b[') and len(reader.mouse_sequence_buffer) >= 3 and data in 'ABCD': 120 | sequence = reader.mouse_sequence_buffer 121 | reader.mouse_sequence_buffer = '' 122 | reader.mouse_sequence_active = False 123 | 124 | if reader.show_recent_menu: 125 | return 126 | 127 | _kill_audio_immediately(reader) 128 | cmd = None 129 | if data == 'C': 130 | cmd = 'next_sentence' 131 | elif data == 'D': 132 | cmd = 'prev_sentence' 133 | elif data == 'B': 134 | cmd = 'next_paragraph' 135 | elif data == 'A': 136 | cmd = 'prev_paragraph' 137 | 138 | if cmd: 139 | reader.loop.call_soon_threadsafe(reader._post_command_sync, cmd) 140 | return 141 | 142 | return 143 | 144 | reader.mouse_sequence_buffer = '' 145 | reader.mouse_sequence_active = False 146 | 147 | # Get keyboard shortcuts 148 | nav_shortcuts = KEYBOARD_SHORTCUTS.get("navigation", {}) 149 | tts_shortcuts = KEYBOARD_SHORTCUTS.get("tts_controls", {}) 150 | display_shortcuts = KEYBOARD_SHORTCUTS.get("display_controls", {}) 151 | app_shortcuts = KEYBOARD_SHORTCUTS.get("application", {}) 152 | 153 | # Map input data to commands using loaded shortcuts 154 | if data == app_shortcuts.get("quit", "q"): 155 | reader.running = False 156 | reader.command_received_event.set() 157 | return 158 | 159 | cmd = None 160 | if data == app_shortcuts.get("toggle_recent_menu", "r"): 161 | cmd = 'toggle_recent_menu' 162 | elif data == app_shortcuts.get("select_menu_item", "\n") or data == '\r': 163 | cmd = 'select_menu_item' 164 | elif data == tts_shortcuts.get("play_pause", "p"): 165 | cmd = 'pause' 166 | elif data == nav_shortcuts.get("prev_paragraph", "h"): 167 | cmd = 'prev_paragraph' 168 | elif data == nav_shortcuts.get("prev_sentence", "j"): 169 | cmd = 'prev_sentence' 170 | elif data == nav_shortcuts.get("next_sentence", "k"): 171 | cmd = 'next_sentence' 172 | elif data == nav_shortcuts.get("next_paragraph", "l"): 173 | cmd = 'next_paragraph' 174 | elif data == nav_shortcuts.get("scroll_page_up", "i"): 175 | cmd = 'scroll_page_up' 176 | elif data == nav_shortcuts.get("scroll_page_down", "m"): 177 | cmd = 'scroll_page_down' 178 | elif data == nav_shortcuts.get("scroll_up", "u"): 179 | cmd = 'scroll_up' 180 | elif data == nav_shortcuts.get("scroll_down", "n"): 181 | cmd = 'scroll_down' 182 | elif data == display_shortcuts.get("toggle_auto_scroll", "a"): 183 | cmd = 'toggle_auto_scroll' 184 | elif data == nav_shortcuts.get("move_to_top_visible", "t"): 185 | cmd = 'move_to_top_visible' 186 | elif data == nav_shortcuts.get("move_to_beginning", "y"): 187 | cmd = 'move_to_beginning' 188 | elif data == nav_shortcuts.get("move_to_end", "b"): 189 | cmd = 'move_to_end' 190 | elif data == tts_shortcuts.get("decrease_speed", ","): 191 | cmd = 'decrease_speed' 192 | elif data == tts_shortcuts.get("increase_speed", "."): 193 | cmd = 'increase_speed' 194 | elif data == tts_shortcuts.get("toggle_sentence_highlight", "s"): 195 | cmd = 'toggle_sentence_highlight' 196 | elif data == tts_shortcuts.get("toggle_word_highlight", "w"): 197 | cmd = 'toggle_word_highlight' 198 | elif data == display_shortcuts.get("cycle_ui_complexity", "v"): 199 | cmd = 'cycle_ui_complexity' 200 | 201 | if cmd: 202 | reader.loop.call_soon_threadsafe(reader._post_command_sync, cmd) 203 | 204 | except Exception: 205 | pass 206 | 207 | def _kill_audio_immediately(reader): 208 | """Kill audio playback immediately.""" 209 | for process in reader.playback_processes[:]: 210 | try: 211 | process.kill() 212 | except (ProcessLookupError, AttributeError): 213 | pass 214 | try: 215 | subprocess.run(['pkill', '-f', 'ffplay'], check=False, 216 | stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL) 217 | except (subprocess.CalledProcessError, FileNotFoundError): 218 | pass -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 |
2 | 3 | Lue Icon 4 | 5 | ### Lue - Terminal eBook Reader with Text-to-Speech 6 | [![License: GPL v3+](https://img.shields.io/badge/License-GPLv3+-86c9fa.svg)](https://www.gnu.org/licenses/gpl-3.0) 7 | [![Python](https://img.shields.io/badge/python-3.10+-86c9fa.svg)](https://www.python.org/downloads/) 8 | [![Platform](https://img.shields.io/badge/platform-macOS%20%7C%20Linux%20%7C%20Windows%20(WSL)-86c9fa)](https://github.com/superstarryeyes/lue) 9 | [![Terminal](https://img.shields.io/badge/interface-terminal-86c9fa.svg)](https://github.com/superstarryeyes/lue) 10 | [![Discord](https://img.shields.io/badge/Discord-Join%20our%20Community-5865F2?logo=discord&logoColor=white)](https://discord.gg/z8sE2gnMNk) 11 | 12 | [Features](#-features) • [Quick Start](#-quick-start-macos-and-linux) • [Installation](#-installation-macos-linux-and-windows) • [Usage](#-usage) • [Customize](#️-customize) • [Development](#-development) 13 | 14 | Lue Screenshot 15 | 16 |
17 | 18 | --- 19 | 20 | ## ✨ Features 21 | 22 | | **Feature** | **Description** | 23 | | --------------------------------------- | ---------------------------------------------------------------------------------------------- | 24 | | **📖 Multi-Format Support** | Support for EPUB, PDF, TXT, DOCX, DOC, HTML, RTF, and Markdown with seamless format detection | 25 | | **👄 Modular TTS System** | Edge TTS (default) and Kokoro TTS (local/offline) with extensible architecture for new models | 26 | | **🌍 Cross-Platform & Multilingual** | Full support for macOS, Linux, Windows (via WSL) with 100+ languages and consistent global experience | 27 | | **🎛️ Speed Adjustment** | Adjust text-to-speech playback speed from 1x to 3x for personalized listening experience | 28 | | **🎯 Auto-Scroll & Precise Word Highlighting** | Automatic scrolling and word-level highlighting synchronized with actual speech, improving focus and concentration | 29 | | **💾 Smart Persistence** | Automatic progress saving, state restoration, and cross-session continuity for seamless reading| 30 | | **⚡️ Fast Navigation** | Intuitive shortcuts, flexible controls, mouse support and optional smooth scrolling for efficient book navigation | 31 | | **⚙️ Extensive Customization** | Fully customizable keyboard layouts (including Vim-style bindings), adjustable UI elements, colors, and display modes| 32 | 33 | --- 34 | 35 | ## 🚀 Quick Start (macOS and Linux) 36 | 37 | > **Want to try Lue right away?** Follow these simple steps: 38 | 39 | ```bash 40 | # 1. Install FFmpeg (required for audio processing) 41 | # macOS 42 | brew install ffmpeg 43 | # Ubuntu/Debian 44 | sudo apt install ffmpeg 45 | 46 | # 2. Install the latest version from PyPI 47 | pip install lue-reader 48 | 49 | # 3. Practice using Lue with the navigation guide 50 | lue --guide 51 | 52 | # 4. Start reading! 53 | lue path/to/your/book.epub 54 | ``` 55 | 56 | > **📝 Note:** Quick start uses Edge TTS (requires internet). For offline capabilities, see [full installation](#-installation-macos-linux-and-windows). 57 | 58 | --- 59 | 60 | ## 📦 Installation (macOS, Linux and Windows) 61 | 62 | ### Prerequisites 63 | 64 | #### Core Requirements 65 | - **FFmpeg** - Audio processing (required) 66 | 67 | #### Optional Dependencies 68 | - **espeak** - Kokoro TTS support 69 | 70 | #### macOS (Homebrew) 71 | ```bash 72 | brew install ffmpeg 73 | # Optional 74 | brew install espeak 75 | ``` 76 | 77 | #### Ubuntu/Debian 78 | ```bash 79 | sudo apt update && sudo apt install ffmpeg 80 | # Optional 81 | sudo apt install espeak 82 | ``` 83 | 84 | #### Arch Linux (AUR) 85 | ```bash 86 | # Using yay 87 | yay -S lue-reader-git 88 | 89 | # Or using paru 90 | paru -S lue-reader-git 91 | ``` 92 | 93 | #### Windows 94 | ```bash 95 | # 1. Install WSL 96 | # Open PowerShell as Administrator: 97 | wsl --install 98 | 99 | # 2. Restart your PC if prompted, then launch Ubuntu from Start Menu 100 | 101 | # 3. Inside Ubuntu terminal: 102 | sudo apt update && sudo apt upgrade -y 103 | sudo apt install ffmpeg python3 python3-pip -y 104 | # Optional 105 | sudo apt install espeak 106 | ``` 107 | 108 | ### Install Lue 109 | 110 | #### Standard Installation 111 | 112 | ```bash 113 | # 1. Clone repository 114 | git clone https://github.com/superstarryeyes/lue.git 115 | cd lue 116 | 117 | # 2. Install dependencies 118 | pip install -r requirements.txt 119 | 120 | # 3. Install Lue 121 | pip install . 122 | ``` 123 | 124 | #### Enable Kokoro TTS (Optional) 125 | 126 | For local/offline TTS capabilities: 127 | 128 | ```bash 129 | # 1. Edit requirements.txt - uncomment Kokoro packages: 130 | kokoro>=0.9.4 131 | soundfile>=0.13.1 132 | huggingface-hub>=0.34.4 133 | 134 | # 2. Install PyTorch 135 | # CPU version: 136 | pip install torch torchvision torchaudio 137 | # GPU version (CUDA): 138 | pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121 139 | 140 | # 3. Install updated requirements 141 | pip install -r requirements.txt 142 | 143 | # 4. Install Lue 144 | pip install . 145 | ``` 146 | 147 | --- 148 | 149 | ## 💻 Usage 150 | 151 | ### Basic Commands 152 | 153 | ```bash 154 | # Start with default TTS 155 | lue path/to/your/book.epub 156 | 157 | # Launch without arguments to open the last book you were reading 158 | lue 159 | 160 | # Practice Lue default keys with the navigation guide 161 | lue --guide 162 | 163 | # View available command line options 164 | lue --help 165 | 166 | # Use specific TTS model (edge/kokoro/none) 167 | lue --tts kokoro path/to/your/book.epub 168 | 169 | # Use a specific voice (full list at VOICES.md) 170 | lue --voice "en-US-AriaNeural" path/to/your/book.epub 171 | 172 | # Set the speech speed (e.g., 1.5x) 173 | lue --speed 1.5 path/to/your/book.epub 174 | 175 | # Specify a language code if needed 176 | lue --lang a path/to/your/book.epub 177 | 178 | # Seconds of overlap between sentences 179 | lue --over 0.2 path/to/your/book.epub 180 | 181 | # Enable PDF cleaning filter (removes page numbers, headers and footnotes, default: 10% (0.1) from both bottom and top of the page) 182 | lue --filter path/to/your/book.pdf 183 | 184 | # Set custom PDF filter margins (0.0-1.0, where 0.1 = 10% of page) 185 | lue --filter 0.15 path/to/your/book.pdf # Both margins to 15% 186 | lue --filter 0.12 0.20 path/to/your/book.pdf # Header 12%, footnote 20% 187 | 188 | # Use the Vim keyboard layout 189 | lue --keys vim path/to/your/book.epub 190 | 191 | ``` 192 | 193 | ### Keyboard Controls (Default) 194 | 195 |
196 | 197 | | **Key Binding** | **Action Description** | 198 | | --------------------------------------- | ---------------------------------------------------------------------------------------------- | 199 | | `q` | Quit the application and save current reading progress automatically | 200 | | `p` | Pause or resume the text-to-speech audio playback | 201 | | `a` | Toggle auto-scroll mode to automatically advance during TTS playback | 202 | | `t` | Select and highlight the top sentence of the current visible page | 203 | | `h` / `l` | Move the reading line to the previous or next paragraph in the document | 204 | | `j` / `k` | Move the reading line to the previous or next sentence in the document | 205 | | `i` / `m` | Jump up or down by full pages for rapid navigation through longer documents | 206 | | `u` / `n` | Scroll up or down by smaller increments for fine-grained position control | 207 | | `y` / `b` | Jump directly to the beginning or end of the document for quick navigation | 208 | | `r` | Open the recent books menu to quickly switch between 5 last read books | 209 | | `,` / `.` | Decrease or increase text-to-speech playback speed (1x to 3x) | 210 | | `s` / `w` | Toggle sentence highlighting or word highlighting on/off | 211 | | `v` | Cycle through UI complexity modes (Minimal, Medium, Full) | 212 | 213 |
214 | 215 | ### Mouse Controls 216 | 217 | - **🖱️ Click** - Jump to sentence 218 | - **🔄 Scroll** - Navigate content 219 | - **📍 Progress bar click** - Jump to position 220 | 221 | ## ⚙️ Customize 222 | 223 | ### UI Modes 224 | 225 | Lue offers three UI complexity modes that you can cycle through using the `v` key or set as your default in the [config.py](lue/config.py) file: 226 | 227 | - **Mode 0 (Minimal)** - Clean text-only display with no borders or UI elements 228 | - **Mode 1 (Medium)** - Displays a top title bar with progress information and borders 229 | - **Mode 2 (Full)** - Full UI with both top title bar and bottom control information 230 | 231 | Additionally, Lue provides customizable word-level and sentence-level highlighting that can be adjusted to suit your reading preferences. You can cycle through different highlighting modes using the `w` and `s` keys. These highlighting settings can also be configured as defaults in the [config.py](lue/config.py) file. 232 | 233 | ### Keyboard Layouts 234 | 235 | Lue comes with two built-in keyboard layouts that can be set using -k/--key command line option or set as your default in the [config.py](lue/config.py) file. You can create your own keyboard layout by copying and modifying one of the existing layout files: 236 | 237 | - **Default Layout** - [keys_default.json](lue/keys_default.json) - Standard keyboard layout 238 | - **Vim Layout** - [keys_vim.json](lue/keys_vim.json) - Vim-style keyboard layout 239 | - **Custom Layout** - Customize your own navigation keys by creating your own keyboard layout json file 240 | 241 | ### Color Themes 242 | 243 | Lue allows you to customize the color theme, visual icons/symbols and all ui elements of the interface by modifying the classes in [ui.py](lue/ui.py). Create your own theme or choose one of the three themes that come with the default installation. 244 | 245 | - **Default Theme** - The default colorful theme with various colors for different UI elements 246 | - **Black Theme** - A dark monochrome theme that's suitable for bright backgrounds 247 | - **White Theme** - A light monochrome theme that's suitable for dark backgrounds 248 | 249 | --- 250 | 251 | ## 🧩 Development 252 | 253 | > **Interested in extending Lue?** 254 | 255 | Check out the [Developer Guide](DEVELOPER.md) for instructions on adding new TTS models and contributing to the project. 256 | 257 | ### Data Storage 258 | 259 | **Reading Progress:** 260 | - **macOS:** `~/Library/Application Support/lue/` 261 | - **Linux:** `~/.local/share/lue/` 262 | - **Windows (WSL):** `~/.local/share/lue/` (within WSL filesystem) 263 | 264 | **Error Logs:** 265 | - **macOS:** `~/Library/Logs/lue/error.log` 266 | - **Linux:** `~/.cache/lue/log/error.log` 267 | - **Windows (WSL):** `~/.cache/lue/log/error.log` (within WSL filesystem) 268 | 269 | --- 270 | 271 | ## 🛠️ Contributing 272 | 273 | Contributions are welcome! Please feel free to submit a Pull Request. 274 | 275 | Join our Discord community for discussions, support and collaboration for creating modules for new TTS models! 276 | 277 | [![Join our Discord](https://img.shields.io/badge/Discord-Join%20Us-5865F2?logo=discord&style=for-the-badge)](https://discord.gg/z8sE2gnMNk) 278 | 279 | --- 280 | 281 | ## 📄 License 282 | 283 | This project is licensed under the **GPL-3.0-or-later License** - see the [LICENSE](LICENSE) file for details. 284 | 285 | --- 286 | 287 |
288 | 289 | Terminal Trove Tool of The Week 290 | 291 | *Made with 💖 for CLI enthusiasts and bookworms* 292 | 293 | **⭐ Star this repo** if you find it useful! 294 | 295 |
296 | -------------------------------------------------------------------------------- /lue/tts/kokoro_tts.py: -------------------------------------------------------------------------------- 1 | import os 2 | import platform 3 | import warnings 4 | import asyncio 5 | import logging 6 | import re 7 | from rich.console import Console 8 | 9 | from .base import TTSBase 10 | from .. import config 11 | 12 | warnings.filterwarnings("ignore") 13 | os.environ["HF_HUB_DISABLE_TELEMETRY"] = "1" 14 | os.environ["HF_HUB_ETAG_TIMEOUT"] = "10" 15 | os.environ["HF_HUB_DOWNLOAD_TIMEOUT"] = "10" 16 | 17 | 18 | class KokoroTTS(TTSBase): 19 | """TTS implementation for Kokoro TTS.""" 20 | 21 | @property 22 | def name(self) -> str: 23 | return "kokoro" 24 | 25 | @property 26 | def output_format(self) -> str: 27 | return "wav" 28 | 29 | def __init__(self, console: Console, voice: str = None, lang: str = None): 30 | super().__init__(console, voice, lang) 31 | self.pipeline = None 32 | self.np = None 33 | self.sf = None 34 | 35 | if self.voice is None: 36 | self.voice = config.TTS_VOICES.get(self.name) 37 | 38 | if self.lang is None: 39 | self.lang = config.TTS_LANGUAGE_CODES.get(self.name) 40 | 41 | def _patch_hf_downloader(self): 42 | """Patches hf_hub_download to show download progress messages.""" 43 | try: 44 | if hasattr(self.huggingface_hub, "_patched_by_lue"): 45 | return 46 | 47 | original_hf_hub_download = self.huggingface_hub.hf_hub_download 48 | 49 | def tracked_hf_hub_download(*args, **kwargs): 50 | try: 51 | local_kwargs = dict(kwargs) 52 | local_kwargs["local_files_only"] = True 53 | original_hf_hub_download(*args, **local_kwargs) 54 | except Exception: 55 | repo_id = kwargs.get("repo_id", "") 56 | filename = kwargs.get("filename", "") 57 | msg = f"[bold yellow]Downloading model '{filename}' from Hugging Face ({repo_id}). This may take a while...[/bold yellow]" 58 | self.console.print(msg) 59 | return original_hf_hub_download(*args, **kwargs) 60 | 61 | self.huggingface_hub.hf_hub_download = tracked_hf_hub_download 62 | self.huggingface_hub._patched_by_lue = True 63 | except Exception as e: 64 | logging.warning(f"Failed to patch Hugging Face downloader: {e}") 65 | 66 | async def initialize(self) -> bool: 67 | """Initializes the Kokoro TTS pipeline asynchronously.""" 68 | try: 69 | import numpy 70 | import soundfile as sf 71 | from kokoro import KPipeline 72 | import huggingface_hub 73 | 74 | self.np = numpy 75 | self.sf = sf 76 | self.KPipeline = KPipeline 77 | self.huggingface_hub = huggingface_hub 78 | except SystemExit: 79 | self.console.print("[bold red]Error: The TTS library exited unexpectedly during import.[/bold red]") 80 | self.console.print("[yellow]This can happen if a required dependency is missing or misconfigured.[/yellow]") 81 | logging.error("SystemExit was called during Kokoro TTS import.") 82 | return False 83 | except ImportError as e: 84 | package = str(e).split("'")[1] 85 | self.console.print(f"[bold red]Error: '{package}' package not found.[/bold red]") 86 | self.console.print(f"[yellow]Please ensure torch, kokoro, soundfile, etc. are installed to use this TTS model.[/yellow]") 87 | logging.error(f"'{package}' is not installed for Kokoro TTS.") 88 | return False 89 | 90 | self._patch_hf_downloader() 91 | loop = asyncio.get_running_loop() 92 | 93 | def _blocking_init(): 94 | gpu_msg, use_gpu = self._get_gpu_acceleration() 95 | pipeline, error_msg, device_used = None, None, None 96 | 97 | if use_gpu: 98 | device_to_try = "mps" if platform.system() == "Darwin" else "cuda" 99 | try: 100 | pipeline = self.KPipeline(repo_id="hexgrad/Kokoro-82M", device=device_to_try, lang_code=self.lang) 101 | device_used = device_to_try 102 | except Exception as gpu_error: 103 | error_msg = f"Failed to initialize on GPU ({device_to_try}): {gpu_error}" 104 | 105 | if pipeline is None: 106 | try: 107 | pipeline = self.KPipeline(repo_id="hexgrad/Kokoro-82M", device="cpu", lang_code=self.lang) 108 | device_used = "cpu" 109 | except Exception as cpu_error: 110 | error_msg = f"Failed to initialize on CPU: {cpu_error}" 111 | 112 | return pipeline, (gpu_msg, error_msg), device_used 113 | 114 | try: 115 | pipeline, (gpu_msg, error_details), device_used = await loop.run_in_executor(None, _blocking_init) 116 | self.console.print(f"[cyan]GPU Check: {gpu_msg}[/cyan]") 117 | 118 | if pipeline: 119 | self.pipeline = pipeline 120 | self.console.print(f"[green]Kokoro TTS model initialized successfully on {device_used}.[/green]") 121 | self.initialized = True 122 | return True 123 | else: 124 | self.console.print(f"[bold red]Kokoro initialization failed.[/bold red]") 125 | if error_details: 126 | self.console.print(f"[red]Error details: {error_details}[/red]") 127 | logging.error(f"Kokoro initialization failed: {error_details}") 128 | return False 129 | except Exception as e: 130 | self.console.print(f"[bold red]An unexpected error occurred during Kokoro's async initialization: {e}[/bold red]") 131 | logging.error("Kokoro async initialization failed.", exc_info=True) 132 | return False 133 | 134 | async def warm_up(self): 135 | """Performs a short TTS generation to load the model into memory.""" 136 | if not self.initialized: 137 | return 138 | 139 | self.console.print("[bold cyan]Warming up the Kokoro TTS model... (this may take a minute)[/bold cyan]") 140 | warmup_file = os.path.join(config.AUDIO_DATA_DIR, f".warmup_kokoro.{self.output_format}") 141 | 142 | try: 143 | await self.generate_audio("Ready.", warmup_file) 144 | self.console.print("[green]Kokoro TTS model is ready.[/green]") 145 | except Exception as e: 146 | self.console.print(f"[bold yellow]Warning: Kokoro model warm-up failed.[/bold yellow]") 147 | logging.warning(f"Kokoro TTS warm-up failed: {e}", exc_info=True) 148 | finally: 149 | if os.path.exists(warmup_file): 150 | try: 151 | os.remove(warmup_file) 152 | except OSError: 153 | pass 154 | 155 | def _get_gpu_acceleration(self): 156 | """Checks for available GPU acceleration.""" 157 | try: 158 | import torch 159 | if torch.cuda.is_available(): 160 | return "NVIDIA CUDA GPU available.", True 161 | if torch.backends.mps.is_available() and platform.system() == "Darwin": 162 | return "Apple Metal (MPS) GPU available.", True 163 | return "No compatible GPU found. Using CPU.", False 164 | except ImportError: 165 | return "PyTorch not found. Using CPU.", False 166 | except Exception as e: 167 | return f"Error checking for GPU ({e}). Using CPU.", False 168 | 169 | async def get_raw_timing_data(self, text: str, output_path: str): 170 | """ 171 | Get raw word timing data from Kokoro TTS. 172 | 173 | Returns: 174 | List of (word, start_time, end_time) tuples with raw timing data from Kokoro TTS 175 | """ 176 | if not self.initialized or not self.pipeline: 177 | raise RuntimeError("Kokoro TTS has not been initialized.") 178 | 179 | def _blocking_generate(): 180 | try: 181 | # Generate audio with timing information 182 | results = list(self.pipeline(text, voice=self.voice, split_pattern=None)) 183 | 184 | if results: 185 | # Concatenate all audio segments 186 | audio_segments = [result.audio for result in results] 187 | full_audio = self.np.concatenate(audio_segments) 188 | self.sf.write(output_path, full_audio, 24000) 189 | 190 | # Extract precise timing information from tokens 191 | word_timings = [] 192 | 193 | # Process each result to extract word-level timing 194 | for result in results: 195 | if hasattr(result, 'tokens') and result.tokens: 196 | # Extract timing from tokens 197 | for token in result.tokens: 198 | # Skip punctuation tokens for word timing 199 | if token.tag in ['.', ',', '!', '?', ':', ';']: 200 | continue 201 | 202 | # Use the actual text and timing from the token 203 | word = token.text 204 | start_time = token.start_ts 205 | end_time = token.end_ts 206 | 207 | # Filter out None values which can cause errors in timing calculations 208 | if start_time is not None and end_time is not None: 209 | # Only include tokens that contain alphanumeric characters 210 | # This ensures consistency with the timing calculator and UI 211 | if re.search(r'[a-zA-Z0-9]', word): 212 | word_timings.append((word, start_time, end_time)) 213 | 214 | return word_timings 215 | else: 216 | self.sf.write(output_path, self.np.array([], dtype=self.np.float32), 24000) 217 | return [] 218 | except Exception as e: 219 | logging.error(f"Error during Kokoro audio generation for text '{text[:50]}...': {e}", exc_info=True) 220 | raise e 221 | 222 | loop = asyncio.get_running_loop() 223 | return await loop.run_in_executor(None, _blocking_generate) 224 | 225 | async def generate_audio_with_timing(self, text: str, output_path: str): 226 | """ 227 | Generate audio with timing using the centralized timing calculator. 228 | 229 | This method leverages Kokoro TTS's token-level timing information 230 | through get_raw_timing_data() and processes it with the timing calculator. 231 | """ 232 | # Get raw timing data (which also generates the audio) 233 | raw_timings = await self.get_raw_timing_data(text, output_path) 234 | 235 | # Get actual audio duration 236 | try: 237 | from .. import audio 238 | except ImportError: 239 | import sys 240 | import os 241 | sys.path.insert(0, os.path.dirname(os.path.dirname(__file__))) 242 | import audio 243 | duration = await audio.get_audio_duration(output_path) 244 | 245 | # Process timing data using the centralized calculator 246 | try: 247 | from ..timing_calculator import process_tts_timing_data 248 | except ImportError: 249 | import sys 250 | import os 251 | sys.path.insert(0, os.path.dirname(os.path.dirname(__file__))) 252 | import timing_calculator 253 | process_tts_timing_data = timing_calculator.process_tts_timing_data 254 | return process_tts_timing_data(text, raw_timings, duration) 255 | 256 | async def generate_audio(self, text: str, output_path: str): 257 | """Generates audio from text using Kokoro in a separate thread.""" 258 | if not self.initialized or not self.pipeline: 259 | raise RuntimeError("Kokoro TTS has not been initialized.") 260 | 261 | def _blocking_generate(): 262 | try: 263 | audio_segments = [result.audio for result in self.pipeline(text, voice=self.voice, split_pattern=None)] 264 | if audio_segments: 265 | full_audio = self.np.concatenate(audio_segments) 266 | self.sf.write(output_path, full_audio, 24000) 267 | else: 268 | self.sf.write(output_path, self.np.array([], dtype=self.np.float32), 24000) 269 | except Exception as e: 270 | logging.error(f"Error during Kokoro audio generation for text '{text[:50]}...': {e}", exc_info=True) 271 | raise e 272 | 273 | loop = asyncio.get_running_loop() 274 | await loop.run_in_executor(None, _blocking_generate) -------------------------------------------------------------------------------- /DEVELOPER.md: -------------------------------------------------------------------------------- 1 | # Lue - Developer Guide: Adding a New TTS Model 2 | 3 | Lue is designed to automatically discover and use any TTS model that adheres to a specific "contract." To add a new model, you only need to create one Python file and edit the configuration. 4 | 5 | The process is: 6 | 1. Create a new file in `lue/tts/` named `yourtts_tts.py`. The filename has to end with `_tts.py`. 7 | 2. Implement a class inside that file that inherits from `TTSBase`. 8 | 3. Add the model's dependencies to `requirements.txt`. 9 | 4. Add a default voice for the model in `config.py`'s `TTS_VOICES` dictionary. 10 | 5. If the model requires a language code, add a default to `config.py`'s `TTS_LANGUAGE_CODES` dictionary. 11 | 12 | ### The `TTSBase` Contract 13 | 14 | Your new class must implement the following properties and methods. The `Lue` application relies on this exact structure to function correctly. 15 | 16 | - `__init__(self, console: Console, voice: str = None, lang: str = None):` 17 | - **Purpose:** The constructor for your TTS model. 18 | - **Rules:** It must accept `console`, `voice`, and `lang` and pass them to the base class constructor: `super().__init__(console, voice, lang)`. The `voice` and `lang` values are passed from the command-line arguments (`--voice` and `--lang`). Not all TTS models support language selection; if yours doesn't, you can simply ignore the `lang` parameter. 19 | 20 | - `@property name(self) -> str:` 21 | - **Purpose:** A unique, lowercase identifier for the model. 22 | - **Rules:** Must match the filename (e.g., if the file is `yourtts_tts.py`, this must return `"yourtts"`). This is used for command-line arguments and configuration keys. 23 | 24 | - `@property output_format(self) -> str:` 25 | - **Purpose:** The audio format the model produces. 26 | - **Rules:** Must be `"mp3"` or `"wav"`. This tells the audio pipeline how to process the output files. 27 | 28 | - `async def initialize(self) -> bool:` 29 | - **Purpose:** Prepare the model. This is where you should handle imports, check for API keys, and load models. 30 | - **Rules:** 31 | - It **must** be asynchronous. 32 | - It **must** gracefully handle a missing dependency by wrapping imports in a `try...except ImportError` block and returning `False`. 33 | - It **must** return `True` on success and `False` on failure. 34 | - For long-running tasks (like downloading models), use `self.console.print()` to give the user feedback. 35 | - If model loading is a blocking operation, it **must** be run in a separate thread to avoid freezing the UI (see template). 36 | 37 | - `async def generate_audio(self, text: str, output_path: str):` 38 | - **Purpose:** The core function that converts a string of text into an audio file. 39 | - **Rules:** 40 | - It **must** be asynchronous. 41 | - It **must** save the generated audio to the exact `output_path` provided. The audio pipeline depends on this file existing after the method completes. 42 | - Like `initialize`, any blocking TTS generation code **must** be run in a separate thread. 43 | 44 | ### Word-Level Timing (Optional Advanced Feature) 45 | 46 | Lue supports word-level highlighting during audio playback, which provides a better reading experience by highlighting each word as it's spoken. The timing logic has been centralized in `lue/timing_calculator.py` to simplify TTS implementations. 47 | 48 | To support word-level highlighting, your TTS model should override the `get_raw_timing_data` method from the `TTSBase` class: 49 | 50 | - `async def get_raw_timing_data(self, text: str, output_path: str):` 51 | - **Purpose:** Extract raw word timing data from your TTS engine and generate the audio file. 52 | - **Return Value:** A list of `(word, start_time, end_time)` tuples with raw timing data from your TTS engine 53 | - **Implementation Guidelines:** 54 | - Generate the audio file and save it to `output_path` 55 | - Extract timing data directly from your TTS engine's output 56 | - Return the raw timing data without any processing or adjustments 57 | - The centralized timing calculator will handle all processing, continuity adjustments, and word mapping 58 | - If your TTS engine doesn't provide timing data, return an empty list `[]` 59 | 60 | The base class `generate_audio_with_timing()` method automatically: 61 | - Calls your `get_raw_timing_data()` method 62 | - Processes the raw timing data using the centralized timing calculator 63 | - Returns a structured dictionary with processed timing information 64 | - Handles fallback estimation if no raw timing data is available 65 | 66 | Example implementation pattern: 67 | 68 | ```python 69 | async def get_raw_timing_data(self, text: str, output_path: str): 70 | """ 71 | Extract raw word timing data from the TTS engine. 72 | """ 73 | # Generate audio and extract raw timing from the TTS engine 74 | result = self.tts_engine.synthesize_with_timing(text, voice=self.voice) 75 | 76 | # Save audio to file 77 | with open(output_path, 'wb') as f: 78 | f.write(result.audio_data) 79 | 80 | # Extract raw word timings from engine results (no processing needed) 81 | word_timings = [] 82 | for word_info in result.word_timings: 83 | word_timings.append(( 84 | word_info.text, # The actual word text 85 | word_info.start, # Start time in seconds (raw from engine) 86 | word_info.end # End time in seconds (raw from engine) 87 | )) 88 | 89 | # Return raw timing data - the timing calculator will handle all processing 90 | return word_timings 91 | ``` 92 | 93 | **Note:** You don't need to implement `generate_audio_with_timing()` unless you have special requirements. The base class implementation automatically uses your `get_raw_timing_data()` method and processes the results through the centralized timing calculator. 94 | 95 | ### Code Template 96 | 97 | Use this template for your `lue/tts/yourtts_tts.py` file. It includes the required structure and best practices for handling errors and blocking operations. 98 | 99 | ```python 100 | # lue/tts/yourtts_tts.py 101 | import os 102 | import asyncio 103 | import logging 104 | from rich.console import Console 105 | 106 | # TODO: Import any other libraries your TTS model needs. 107 | 108 | from .base import TTSBase 109 | from .. import config 110 | 111 | class YourTTSTTS(TTSBase): 112 | """ 113 | A brief description of your TTS model and what it does. 114 | """ 115 | 116 | @property 117 | def name(self) -> str: 118 | # Must match the filename: yourtts_tts.py -> "yourtts" 119 | return "yourtts" 120 | 121 | @property 122 | def output_format(self) -> str: 123 | # The audio format your model produces ("mp3" or "wav") 124 | return "mp3" 125 | 126 | def __init__(self, console: Console, voice: str = None, lang: str = None): 127 | super().__init__(console, voice, lang) 128 | self.client = None # Example: an API client or model object 129 | 130 | # If the user doesn't provide a voice via --voice, use the default from config.py 131 | if self.voice is None: 132 | self.voice = config.TTS_VOICES.get(self.name) 133 | 134 | # If the user doesn't provide a language via --lang, use the default from config.py 135 | # Only use self.lang if your TTS model actually supports it. 136 | if self.lang is None: 137 | self.lang = config.TTS_LANGUAGE_CODES.get(self.name) 138 | 139 | async def initialize(self) -> bool: 140 | """ 141 | Prepare the model. Check dependencies, load models, etc. 142 | """ 143 | # 1. Check for dependencies and handle failure gracefully. 144 | try: 145 | # TODO: Import the actual TTS library here. 146 | # from your_tts_library import YourTTSClient 147 | pass # Replace with actual import 148 | except ImportError: 149 | self.console.print("[bold red]Error: 'your_tts_library' package not found.[/bold red]") 150 | self.console.print("[yellow]Please install it with 'pip install your_tts_library'[/yellow]") 151 | logging.error("'your_tts_library' is not installed.") 152 | return False 153 | 154 | # 2. For heavy/blocking setup tasks (like downloading or loading a large model), 155 | # run them in a separate thread to keep the UI responsive. 156 | loop = asyncio.get_running_loop() 157 | try: 158 | self.console.print("[cyan]Initializing YourTTS model... (this may take a moment)[/cyan]") 159 | 160 | # This is a synchronous function to do the heavy lifting. 161 | def _blocking_init(): 162 | # TODO: Replace with your actual model loading logic. 163 | # For example, check for API keys or load a model using self.lang 164 | # client = YourTTSClient(api_key=os.environ.get("YOURTTS_API_KEY"), language=self.lang) 165 | # return client 166 | return True # Return the client/model object on success 167 | 168 | # Run the blocking function in an executor. 169 | self.client = await loop.run_in_executor(None, _blocking_init) 170 | 171 | if not self.client: 172 | self.console.print("[bold red]YourTTS initialization failed. Check logs for details.[/bold red]") 173 | return False 174 | 175 | self.initialized = True 176 | self.console.print("[green]YourTTS model initialized successfully.[/green]") 177 | return True 178 | except Exception as e: 179 | self.console.print(f"[bold red]An unexpected error occurred during YourTTS initialization: {e}[/bold red]") 180 | logging.error("YourTTS async initialization failed.", exc_info=True) 181 | return False 182 | 183 | async def generate_audio(self, text: str, output_path: str): 184 | """ 185 | Generate audio from text and save it to the given path. 186 | """ 187 | if not self.initialized or not self.client: 188 | raise RuntimeError("YourTTS has not been initialized.") 189 | 190 | # This is a synchronous function to do the audio generation. 191 | def _blocking_generate(): 192 | try: 193 | # TODO: Replace with your library's actual audio generation call. 194 | # Use self.voice, which was set in __init__ 195 | # The final audio MUST be saved to the `output_path`. 196 | # audio_data = self.client.generate(text=text, voice=self.voice) 197 | # with open(output_path, "wb") as f: 198 | # f.write(audio_data) 199 | pass # Replace with actual generation 200 | except Exception as e: 201 | logging.error(f"Error during YourTTS audio generation: {e}", exc_info=True) 202 | raise e 203 | 204 | # Run the blocking generation in a separate thread. 205 | loop = asyncio.get_running_loop() 206 | await loop.run_in_executor(None, _blocking_generate) 207 | 208 | # Optional: Implement word-level timing for better highlighting accuracy 209 | async def get_raw_timing_data(self, text: str, output_path: str): 210 | """ 211 | Extract raw word timing data from your TTS engine. 212 | 213 | This method is optional but recommended for better word highlighting accuracy. 214 | If not implemented, the base class will use fallback estimation. 215 | 216 | Returns: 217 | List of (word, start_time, end_time) tuples with raw timing data from TTS engine, 218 | or empty list if no timing data is available 219 | """ 220 | # TODO: Implement actual timing extraction from your TTS engine 221 | # The example below shows the structure but should be replaced with 222 | # actual implementation based on your TTS engine's capabilities. 223 | 224 | # This is a synchronous function to do the audio generation with timing. 225 | def _blocking_generate(): 226 | try: 227 | # TODO: Replace with your library's actual audio generation call that provides timing. 228 | # Use self.voice, which was set in __init__ 229 | # The final audio MUST be saved to the `output_path`. 230 | 231 | # Example with a hypothetical TTS engine that provides timing: 232 | # result = self.client.generate_with_timing(text=text, voice=self.voice) 233 | # with open(output_path, "wb") as f: 234 | # f.write(result.audio_data) 235 | 236 | # Extract raw timing data from your TTS engine 237 | # word_timings = [] 238 | # for word_info in result.word_timings: 239 | # word_timings.append(( 240 | # word_info.text, # The actual word text 241 | # word_info.start, # Start time in seconds (raw from engine) 242 | # word_info.end # End time in seconds (raw from engine) 243 | # )) 244 | # return word_timings 245 | 246 | # If your TTS engine doesn't provide timing, fall back to regular generation 247 | # and return empty list (the timing calculator will estimate) 248 | # TODO: Replace with actual generation 249 | pass # Replace with actual generation 250 | return [] # Return empty list if no timing available 251 | 252 | except Exception as e: 253 | logging.error(f"Error during YourTTS audio generation: {e}", exc_info=True) 254 | raise e 255 | 256 | # Run the blocking generation in a separate thread. 257 | loop = asyncio.get_running_loop() 258 | return await loop.run_in_executor(None, _blocking_generate) 259 | 260 | ``` -------------------------------------------------------------------------------- /lue/__main__.py: -------------------------------------------------------------------------------- 1 | """Main entry point for the Lue eBook reader application.""" 2 | 3 | import asyncio 4 | import sys 5 | import termios 6 | import tty 7 | import subprocess 8 | import argparse 9 | import os 10 | import platform 11 | import platformdirs 12 | import logging 13 | try: 14 | from importlib.resources import files 15 | except ImportError: 16 | # Fallback for Python < 3.9 17 | from importlib_resources import files 18 | from rich.console import Console 19 | from .reader import Lue 20 | from . import config, progress_manager, input_handler 21 | from .tts_manager import TTSManager, get_default_tts_model_name 22 | 23 | def get_keyboard_shortcuts_file(keys_arg): 24 | """Resolve the keyboard shortcuts file path from the command line argument.""" 25 | # If it's a direct file path that exists, use it 26 | if os.path.isfile(keys_arg): 27 | return keys_arg 28 | 29 | # If it's a preset name, look for keys_{name}.json in the lue directory 30 | preset_file = os.path.join(os.path.dirname(__file__), f'keys_{keys_arg}.json') 31 | if os.path.isfile(preset_file): 32 | return preset_file 33 | 34 | # If it's the special "default" name, use keys_default.json 35 | if keys_arg == "default": 36 | default_file = os.path.join(os.path.dirname(__file__), 'keys_default.json') 37 | if os.path.isfile(default_file): 38 | return default_file 39 | 40 | # Fallback to default 41 | return os.path.join(os.path.dirname(__file__), 'keys_default.json') 42 | 43 | def get_guide_file_path(): 44 | """Get the path to the guide file, creating a temporary file if needed for packaged installs.""" 45 | import tempfile 46 | 47 | try: 48 | # Try to get the guide from the package data first (for pip installs) 49 | try: 50 | guide_file = files('lue') / 'guide.txt' 51 | guide_content = guide_file.read_text(encoding='utf-8') 52 | 53 | # Create a temporary file with a user-friendly name 54 | temp_dir = tempfile.gettempdir() 55 | temp_path = os.path.join(temp_dir, "Lue Navigation Guide.txt") 56 | 57 | with open(temp_path, 'w', encoding='utf-8') as temp_file: 58 | temp_file.write(guide_content) 59 | 60 | return temp_path 61 | 62 | except (FileNotFoundError, ModuleNotFoundError): 63 | # Fallback to local file (for development) 64 | guide_path = os.path.join(os.path.dirname(__file__), 'guide.txt') 65 | if os.path.exists(guide_path): 66 | return guide_path 67 | else: 68 | return None 69 | 70 | except Exception: 71 | return None 72 | 73 | def setup_logging(): 74 | """Set up file-based logging for the application.""" 75 | log_dir = platformdirs.user_log_dir(appname="lue", appauthor=False) 76 | os.makedirs(log_dir, exist_ok=True) 77 | log_file = os.path.join(log_dir, "error.log") 78 | 79 | logging.basicConfig( 80 | level=logging.INFO, 81 | format='%(asctime)s - %(levelname)s - %(name)s - %(message)s', 82 | filename=log_file, 83 | filemode='a', 84 | force=True, 85 | ) 86 | logging.info("Application starting") 87 | 88 | def setup_environment(): 89 | """Set environment variables for TTS models.""" 90 | os.environ["HF_HUB_DISABLE_TELEMETRY"] = "1" 91 | os.environ["HF_HUB_ETAG_TIMEOUT"] = "10" 92 | os.environ["HF_HUB_DOWNLOAD_TIMEOUT"] = "10" 93 | os.environ["HF_HUB_DISABLE_SYMLINKS_WARNING"] = "1" 94 | if platform.system() == "Darwin" and platform.processor() == "arm": 95 | os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1" 96 | 97 | def preprocess_filter_args(args): 98 | """Preprocess arguments to handle --filter with space-separated values.""" 99 | processed_args = [] 100 | i = 0 101 | while i < len(args): 102 | arg = args[i] 103 | if arg in ['--filter', '-f']: 104 | # Found filter argument 105 | processed_args.append(arg) 106 | i += 1 107 | 108 | # Collect numeric values that follow 109 | filter_values = [] 110 | while i < len(args): 111 | try: 112 | # Try to parse as float 113 | float(args[i]) 114 | filter_values.append(args[i]) 115 | i += 1 116 | if len(filter_values) >= 2: # Max 2 values 117 | break 118 | except ValueError: 119 | # Not a number, stop collecting 120 | break 121 | 122 | # Join the values and add as a single argument 123 | if filter_values: 124 | processed_args.append(' '.join(filter_values)) 125 | else: 126 | # No values provided, add empty string 127 | processed_args.append('') 128 | else: 129 | processed_args.append(arg) 130 | i += 1 131 | 132 | return processed_args 133 | 134 | async def main(): 135 | # Preprocess arguments to handle filter syntax 136 | preprocessed_args = preprocess_filter_args(sys.argv[1:]) 137 | 138 | tts_manager = TTSManager() 139 | available_tts = tts_manager.get_available_tts_names() 140 | default_tts = get_default_tts_model_name(available_tts) 141 | 142 | parser = argparse.ArgumentParser( 143 | description="A terminal-based eBook reader with TTS", 144 | add_help=False # Disable automatic help to add custom one 145 | ) 146 | 147 | parser.add_argument( 148 | '-h', '--help', 149 | action='help', 150 | help='Show this help message and exit' 151 | ) 152 | 153 | parser.add_argument( 154 | '-g', '--guide', 155 | action='store_true', 156 | help='Open the keyboard shortcuts navigation guide' 157 | ) 158 | 159 | parser.add_argument("file_path", nargs='?', help="Path to the eBook file (.epub, .pdf, .txt, etc.). If not provided, opens the last book you were reading.") 160 | parser.add_argument( 161 | "-f", 162 | "--filter", 163 | nargs='?', 164 | const='', 165 | help="Enable PDF text cleaning filters. Usage: --filter (defaults), --filter 0.15 (both margins), --filter 0.12 0.20 (header, footnote)", 166 | ) 167 | 168 | parser.add_argument( 169 | "-o", "--over", type=float, help="Seconds of overlap between sentences" 170 | ) 171 | 172 | parser.add_argument( 173 | "-k", "--keys", 174 | help="Keyboard configuration. Use a preset name (vim, default) or a path to a JSON file. Default: default", 175 | default="default" 176 | ) 177 | 178 | if available_tts: 179 | # Add "none" option to available TTS choices 180 | tts_choices = ["none"] + available_tts 181 | parser.add_argument( 182 | "-t", 183 | "--tts", 184 | choices=tts_choices, 185 | default=default_tts, 186 | help=f"Select the Text-to-Speech model. Use 'none' to disable TTS (default: {default_tts})", 187 | ) 188 | parser.add_argument( 189 | "-v", 190 | "--voice", 191 | help="Specify the voice for the TTS model", 192 | ) 193 | parser.add_argument( 194 | "-s", 195 | "--speed", 196 | type=float, 197 | default=1.0, 198 | help="Set the speech speed (default: 1.0)", 199 | ) 200 | parser.add_argument( 201 | "-l", 202 | "--lang", 203 | help="Specify the language for the TTS model", 204 | ) 205 | args = parser.parse_args(preprocessed_args) 206 | 207 | # Initialize console early for printing messages 208 | console = Console() 209 | 210 | # Handle guide argument - open guide file in Lue app 211 | if args.guide: 212 | guide_path = get_guide_file_path() 213 | if guide_path: 214 | console.print("[green]Opening navigation guide...[/green]") 215 | args.file_path = guide_path 216 | else: 217 | console.print("[red]Guide file not found.[/red]") 218 | sys.exit(1) 219 | # Handle the case when no file is provided - try to open the last book 220 | elif not args.file_path: 221 | last_book_path = progress_manager.find_most_recent_book() 222 | if last_book_path: 223 | console.print(f"[green]Opening last book: {os.path.basename(last_book_path)}[/green]") 224 | args.file_path = last_book_path 225 | else: 226 | console.print("[red]No file specified and no previous books found.[/red]") 227 | console.print("Please provide a file path as an argument.") 228 | parser.print_help() 229 | sys.exit(1) 230 | else: 231 | # Convert relative path to absolute path for consistency 232 | args.file_path = os.path.abspath(args.file_path) 233 | 234 | if args.over is not None: 235 | config.OVERLAP_SECONDS = args.over 236 | 237 | # Handle PDF filter settings 238 | if args.filter is not None: 239 | config.PDF_FILTERS_ENABLED = True 240 | 241 | if args.filter == '': 242 | # Just --filter with no values, use defaults 243 | pass 244 | else: 245 | # Parse the filter values 246 | try: 247 | filter_values = [float(x.strip()) for x in args.filter.split() if x.strip()] 248 | 249 | if len(filter_values) == 1: 250 | # One number provided - set both margins to this value 251 | config.PDF_HEADER_MARGIN = filter_values[0] 252 | config.PDF_FOOTNOTE_MARGIN = filter_values[0] 253 | elif len(filter_values) == 2: 254 | # Two numbers provided - set header and footnote margins separately 255 | config.PDF_HEADER_MARGIN = filter_values[0] 256 | config.PDF_FOOTNOTE_MARGIN = filter_values[1] 257 | elif len(filter_values) > 2: 258 | console.print("[red]Error: --filter accepts at most 2 values (header margin, footnote margin)[/red]") 259 | sys.exit(1) 260 | except ValueError: 261 | console.print(f"[red]Error: Invalid filter values '{args.filter}'. Expected float numbers.[/red]") 262 | sys.exit(1) 263 | 264 | setup_environment() 265 | setup_logging() 266 | 267 | 268 | for tool in ['ffprobe', 'ffplay', 'ffmpeg']: 269 | try: 270 | subprocess.run([tool, '-version'], check=True, text=True, 271 | stderr=subprocess.DEVNULL, stdout=subprocess.DEVNULL) 272 | except (subprocess.CalledProcessError, FileNotFoundError): 273 | console.print(f"\n[bold red]Error: {tool} not found.[/bold red] " 274 | "Please install FFmpeg and ensure it's in your system's PATH.") 275 | logging.error(f"Required tool '{tool}' not found. FFmpeg may not be installed.") 276 | sys.exit(1) 277 | 278 | # Resolve keyboard shortcuts file 279 | # Prioritize command-line argument if explicitly provided (not the default) 280 | if args.keys != "default": 281 | # User explicitly provided a keys argument 282 | keyboard_shortcuts_file = get_keyboard_shortcuts_file(args.keys) 283 | elif config.CUSTOM_KEYBOARD_SHORTCUTS and config.CUSTOM_KEYBOARD_SHORTCUTS != "default": 284 | # Use the config value if it's not the default 285 | keyboard_shortcuts_file = get_keyboard_shortcuts_file(config.CUSTOM_KEYBOARD_SHORTCUTS) 286 | else: 287 | # Fall back to default 288 | keyboard_shortcuts_file = get_keyboard_shortcuts_file("default") 289 | 290 | # Load keyboard shortcuts 291 | input_handler.load_keyboard_shortcuts(keyboard_shortcuts_file) 292 | 293 | tts_instance = None 294 | if available_tts and hasattr(args, 'tts') and args.tts and args.tts != "none": 295 | voice = args.voice if hasattr(args, 'voice') else None 296 | lang = args.lang if hasattr(args, 'lang') else None 297 | tts_instance = tts_manager.create_model(args.tts, console, voice=voice, lang=lang) 298 | 299 | reader = Lue(args.file_path, tts_model=tts_instance, overlap=args.over) 300 | if hasattr(args, 'speed'): 301 | reader.playback_speed = args.speed 302 | 303 | # Hide cursor, enable mouse tracking 304 | sys.stdout.write('\033[?1000h\033[?1006h\033[?25l') 305 | sys.stdout.flush() 306 | 307 | fd = sys.stdin.fileno() 308 | old_settings = termios.tcgetattr(fd) 309 | temp_guide_file = None 310 | 311 | # Check if we're using a temporary guide file 312 | if args.guide and args.file_path and "Lue Navigation Guide.txt" in args.file_path: 313 | temp_guide_file = args.file_path 314 | 315 | try: 316 | tty.setcbreak(sys.stdin.fileno()) 317 | 318 | initialized = await reader.initialize_tts() 319 | if not initialized and hasattr(args, 'tts') and args.tts and args.tts != "none": 320 | console.print(f"[bold yellow]Warning: TTS model '{args.tts}' " 321 | "failed to initialize and has been disabled.[/bold yellow]") 322 | 323 | await reader.run() 324 | 325 | finally: 326 | sys.stdout.write('\033[?1000l\033[?1006l\033[?25h') 327 | sys.stdout.flush() 328 | if fd is not None and old_settings is not None: 329 | termios.tcsetattr(fd, termios.TCSADRAIN, old_settings) 330 | 331 | # Clean up temporary guide file if it was created 332 | if temp_guide_file: 333 | try: 334 | os.unlink(temp_guide_file) 335 | except (OSError, FileNotFoundError): 336 | pass 337 | 338 | def cli(): 339 | """Synchronous entry point for the command-line interface.""" 340 | try: 341 | asyncio.run(main()) 342 | except (KeyboardInterrupt, SystemExit): 343 | pass 344 | except Exception as e: 345 | logging.critical(f"Fatal error in application startup: {e}", exc_info=True) 346 | 347 | if __name__ == "__main__": 348 | cli() 349 | -------------------------------------------------------------------------------- /lue/audio.py: -------------------------------------------------------------------------------- 1 | import asyncio 2 | import os 3 | import re 4 | import subprocess 5 | import logging 6 | from . import config, content_parser 7 | 8 | # This pattern is used to both clean text for TTS and detect sentence fragments. 9 | ABBREVIATION_PATTERN = r'\b(Mr|Mrs|Ms|Dr|Prof|Rev|Hon|Jr|Sr|Cpl|Sgt|Gen|Col|Capt|Lt|Pvt|vs|viz|Co|Inc|Ltd|Corp|St|Ave|Blvd)\.' 10 | INITIAL_PATTERN = r'\b([A-Z])\.(?=\s[A-Z])' 11 | 12 | 13 | # Word mapping functionality moved to timing_calculator.py 14 | # Import it here for backward compatibility 15 | from .timing_calculator import create_word_mapping as _create_word_mapping 16 | 17 | 18 | def clean_tts_text(text: str) -> str: 19 | """ 20 | Removes periods from specific English abbreviations and single initials 21 | to prevent unnatural pauses in TTS engines. Also removes loose punctuation 22 | marks that are not connected to any word. 23 | """ 24 | # Remove periods from abbreviations and initials 25 | text = re.sub(ABBREVIATION_PATTERN, r'\1', text) 26 | text = re.sub(INITIAL_PATTERN, r'\1 ', text) 27 | 28 | # Remove loose punctuation marks that are standalone (not connected to words) 29 | # This pattern matches punctuation that is surrounded by whitespace or at string boundaries 30 | text = re.sub(r'(?:^|\s)[.,:;!?]+(?=\s|$)', ' ', text) 31 | 32 | # Remove standalone dashes that are followed by quotation marks 33 | # This prevents TTS engines from reading "-" as "dash" in cases like: -" 34 | text = re.sub(r'(?:^|\s)-(?=")', ' ', text) 35 | 36 | # Clean up any extra whitespace that might result from removing punctuation 37 | text = re.sub(r'\s+', ' ', text).strip() 38 | 39 | return text 40 | 41 | async def stop_and_clear_audio(reader): 42 | """Stop audio playback and clear the audio queue.""" 43 | tasks_to_cancel = [] 44 | for task in [reader.producer_task, reader.player_task]: 45 | if task and not task.done(): 46 | task.cancel() 47 | tasks_to_cancel.append(task) 48 | if tasks_to_cancel: 49 | await asyncio.gather(*tasks_to_cancel, return_exceptions=True) 50 | 51 | reader.producer_task = None 52 | reader.player_task = None 53 | 54 | processes_to_kill = reader.playback_processes.copy() 55 | reader.playback_processes.clear() 56 | for process in processes_to_kill: 57 | try: 58 | if process.returncode is None: 59 | process.terminate() 60 | try: await asyncio.wait_for(process.wait(), timeout=0.2) 61 | except asyncio.TimeoutError: 62 | process.kill() 63 | await asyncio.wait_for(process.wait(), timeout=0.1) 64 | except (ProcessLookupError, AttributeError, asyncio.TimeoutError): pass 65 | 66 | try: 67 | pkill_proc = await asyncio.create_subprocess_exec('pkill', '-9', '-f', 'ffplay.*buffer_', stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL) 68 | await asyncio.wait_for(pkill_proc.wait(), timeout=0.3) 69 | except (FileNotFoundError, asyncio.TimeoutError): pass 70 | 71 | while not reader.audio_queue.empty(): 72 | try: 73 | reader.audio_queue.get_nowait() 74 | reader.audio_queue.task_done() 75 | except asyncio.QueueEmpty: break 76 | 77 | await asyncio.sleep(0.1) 78 | 79 | # More aggressive cleanup with longer delays for file system operations 80 | for buf_base in config.AUDIO_BUFFERS: 81 | for ext in ['.mp3', '.wav']: 82 | buf = f"{buf_base}{ext}" 83 | for attempt in range(5): # Increased attempts 84 | try: 85 | if os.path.exists(buf): 86 | os.remove(buf) 87 | break 88 | except OSError: 89 | if attempt < 4: 90 | await asyncio.sleep(0.1) # Longer delay 91 | 92 | 93 | 94 | await asyncio.sleep(0.2) # Longer final delay 95 | 96 | 97 | 98 | async def get_audio_duration(file_path): 99 | """Get the duration of an audio file.""" 100 | command = ['ffprobe', '-v', 'error', '-show_entries', 'format=duration', '-of', 'default=noprint_wrappers=1:nokey=1', file_path] 101 | process = await asyncio.create_subprocess_exec(*command, stdout=asyncio.subprocess.PIPE, stderr=subprocess.DEVNULL) 102 | stdout, _ = await process.communicate() 103 | if process.returncode != 0: return None 104 | try: return float(stdout.decode().strip()) 105 | except (ValueError, TypeError): return None 106 | 107 | async def play_from_current_position(reader): 108 | """Start the audio producer and player loops.""" 109 | if not reader.is_paused and reader.running and reader.tts_model: 110 | # Cancel existing tasks and wait for them to complete 111 | for task in [reader.producer_task, reader.player_task]: 112 | if task and not task.done(): 113 | task.cancel() 114 | try: 115 | await asyncio.wait_for(task, timeout=2.0) 116 | except (asyncio.CancelledError, asyncio.TimeoutError): 117 | pass 118 | 119 | # Ensure tasks are properly cleaned up 120 | reader.producer_task = None 121 | reader.player_task = None 122 | 123 | # Small delay to ensure cleanup is complete 124 | await asyncio.sleep(0.05) 125 | 126 | reader.producer_task = asyncio.create_task(_producer_loop(reader)) 127 | reader.player_task = asyncio.create_task(_player_loop(reader)) 128 | 129 | async def _producer_loop(reader): 130 | """Producer loop to generate audio files.""" 131 | if not reader.tts_model or not reader.tts_model.initialized: 132 | try: await asyncio.wait_for(reader.audio_queue.put(None), timeout=0.5) 133 | except (asyncio.TimeoutError, asyncio.CancelledError): pass 134 | return 135 | 136 | producer_pos = (reader.chapter_idx, reader.paragraph_idx, reader.sentence_idx) 137 | buffer_index = 0 138 | try: 139 | while reader.running: 140 | if reader.audio_queue.full(): 141 | await asyncio.sleep(0.1) 142 | continue 143 | try: 144 | c, p, s = producer_pos 145 | sentences = content_parser.split_into_sentences(reader.chapters[c][p]) 146 | text = sentences[s] 147 | except IndexError: break 148 | if not text or not text.strip(): 149 | next_pos = reader._advance_position(producer_pos, wrap=False) 150 | if not next_pos: break 151 | producer_pos = next_pos 152 | continue 153 | 154 | # --- Start of fragment merging logic --- 155 | merged = False 156 | # Heuristic: if a "sentence" is just an abbreviation, it might be a fragment. 157 | # We check if the entire text matches common abbreviation patterns. 158 | is_abbrev_fragment = re.fullmatch(ABBREVIATION_PATTERN, text.strip()) 159 | 160 | if is_abbrev_fragment and s + 1 < len(sentences): 161 | text += " " + sentences[s+1] 162 | merged = True 163 | # --- End of fragment merging logic --- 164 | 165 | # Preserve original text for UI display and timing calculation 166 | original_text = text 167 | 168 | output_format = reader.tts_model.output_format 169 | output_filename = f"{config.AUDIO_BUFFERS[buffer_index]}.{output_format}" 170 | 171 | try: 172 | if not reader.running: break 173 | 174 | for attempt in range(3): 175 | try: 176 | if os.path.exists(output_filename): os.remove(output_filename) 177 | break 178 | except OSError: 179 | if attempt < 2: await asyncio.sleep(0.05) 180 | 181 | # Create sanitized version for TTS 182 | sanitized_text = content_parser.sanitize_text_for_tts(original_text) 183 | 184 | timing_info = None 185 | 186 | # Use the timing-aware method if available 187 | if hasattr(reader.tts_model, 'generate_audio_with_timing'): 188 | try: 189 | timing_info = await reader.tts_model.generate_audio_with_timing(sanitized_text, output_filename) 190 | except Exception as e: 191 | # If timing generation fails, fall back to generating without it 192 | logging.error(f"TTS timing generation failed for text '{original_text[:50]}...' (sanitized: '{sanitized_text[:50]}...'): {e}") 193 | await reader.tts_model.generate_audio(sanitized_text, output_filename) 194 | else: 195 | # Fallback to regular method 196 | await reader.tts_model.generate_audio(sanitized_text, output_filename) 197 | 198 | # Always get the actual duration from the file 199 | duration = await get_audio_duration(output_filename) 200 | 201 | if not reader.running: break 202 | 203 | # If no timing info was generated, create a fallback structure 204 | # Pass original_text to timing calculator for proper word mapping 205 | if timing_info is None: 206 | from .timing_calculator import process_tts_timing_data 207 | timing_info = process_tts_timing_data(original_text, [], duration) 208 | 209 | await asyncio.wait_for(reader.audio_queue.put((output_filename, *producer_pos, duration, timing_info)), timeout=1.0) 210 | 211 | next_pos = reader._advance_position(producer_pos, wrap=False) 212 | if merged: 213 | # If we merged two sentences, we must advance the position an extra time. 214 | if next_pos: 215 | next_pos = reader._advance_position(next_pos, wrap=False) 216 | 217 | if not next_pos: break 218 | producer_pos = next_pos 219 | buffer_index = (buffer_index + 1) % len(config.AUDIO_BUFFERS) 220 | except asyncio.CancelledError: break 221 | except Exception as e: 222 | if reader.running: 223 | # Include both original and sanitized text in error logging 224 | try: 225 | sanitized_for_log = content_parser.sanitize_text_for_tts(original_text) if 'original_text' in locals() else 'N/A' 226 | original_for_log = original_text if 'original_text' in locals() else 'N/A' 227 | logging.error(f"TTS Error in producer: {e}\nOriginal text: '{original_for_log[:100]}...'\nSanitized text: '{sanitized_for_log[:100]}...'", exc_info=True) 228 | except: 229 | logging.error(f"TTS Error in producer: {e}", exc_info=True) 230 | await asyncio.sleep(2) 231 | continue 232 | except asyncio.CancelledError: pass 233 | finally: 234 | try: await asyncio.wait_for(reader.audio_queue.put(None), timeout=0.5) 235 | except (asyncio.TimeoutError, asyncio.CancelledError): pass 236 | 237 | async def _player_loop(reader): 238 | """Player loop to play audio files.""" 239 | try: 240 | while reader.running: 241 | try: 242 | item = await asyncio.wait_for(reader.audio_queue.get(), timeout=1.0) 243 | if item is None: 244 | reader.audio_queue.task_done() 245 | if reader.active_playback_tasks: 246 | await asyncio.gather(*reader.active_playback_tasks, return_exceptions=True) 247 | reader.playback_finished_event.set() 248 | break 249 | # Unpack the queue item 250 | audio_file, c, p, s, duration, timing_data = item 251 | if isinstance(timing_data, dict): 252 | timing_info = timing_data 253 | else: 254 | # Old format, timing_data is word_timings 255 | timing_info = {"word_timings": timing_data, "speech_duration": duration, "total_duration": duration} 256 | 257 | word_timings = timing_info.get("word_timings", []) 258 | 259 | if not os.path.exists(audio_file): 260 | reader.audio_queue.task_done() 261 | continue 262 | if duration is None or duration <= 0: 263 | reader.audio_queue.task_done() 264 | continue 265 | try: 266 | # Post a command to the main loop to handle the state transition atomically 267 | reader.loop.call_soon_threadsafe( 268 | reader._post_command_sync, 269 | ('_new_sentence_started', (c, p, s, duration, timing_data)) 270 | ) 271 | except RuntimeError: 272 | reader.audio_queue.task_done() 273 | break 274 | try: 275 | # Build ffplay command with speed control using atempo filter 276 | cmd = ['ffplay', '-nodisp', '-autoexit', '-loglevel', 'error'] 277 | 278 | # Add atempo filter if speed is not 1.0 279 | if abs(reader.playback_speed - 1.0) > 0.01: 280 | # atempo filter has limitations: must be between 0.5 and 2.0 281 | # For speeds outside this range, we chain multiple atempo filters 282 | speed = reader.playback_speed 283 | filters = [] 284 | 285 | while speed > 2.0: 286 | filters.append('atempo=2.0') 287 | speed /= 2.0 288 | while speed < 0.5: 289 | filters.append('atempo=0.5') 290 | speed /= 0.5 291 | if abs(speed - 1.0) > 0.01: 292 | filters.append(f'atempo={speed:.3f}') 293 | 294 | if filters: 295 | filter_chain = ','.join(filters) 296 | cmd.extend(['-af', filter_chain]) 297 | 298 | cmd.append(audio_file) 299 | process = await asyncio.create_subprocess_exec(*cmd, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL) 300 | reader.playback_processes.append(process) 301 | except Exception: 302 | reader.audio_queue.task_done() 303 | continue 304 | 305 | async def await_and_remove(proc, file): 306 | task = asyncio.current_task() 307 | try: 308 | await proc.wait() 309 | except Exception: pass 310 | finally: 311 | try: 312 | if proc in reader.playback_processes: reader.playback_processes.remove(proc) 313 | except ValueError: pass 314 | for attempt in range(3): 315 | try: 316 | if os.path.exists(file): os.remove(file) 317 | break 318 | except OSError: 319 | if attempt < 2: await asyncio.sleep(0.05) 320 | if task in reader.active_playback_tasks: 321 | reader.active_playback_tasks.remove(task) 322 | 323 | playback_task = asyncio.create_task(await_and_remove(process, audio_file)) 324 | reader.active_playback_tasks.append(playback_task) 325 | 326 | # Calculate dynamic overlap based on playback speed 327 | # Overlap should decrease as speed increases, reaching 0 at 3.00x speed and beyond 328 | base_overlap = config.OVERLAP_SECONDS 329 | if reader.tts_model and hasattr(reader.tts_model, 'get_overlap_seconds'): 330 | tts_overlap = reader.tts_model.get_overlap_seconds() 331 | if tts_overlap is not None: 332 | base_overlap = tts_overlap 333 | 334 | # Apply speed-based overlap reduction 335 | # At 1.0x speed: full overlap 336 | # At 3.00x speed and above: 0 overlap 337 | # Linear decrease between 1.0x and 3.0x 338 | speed = reader.playback_speed 339 | if speed >= 3.0: 340 | overlap_seconds = 0.0 341 | else: 342 | # Calculate overlap as a linear function decreasing from base_overlap to 0 343 | # as speed increases from 1.0 to 3.0 344 | overlap_factor = max(0.0, min(1.0, (3.0 - speed) / (3.0 - 1.0))) 345 | overlap_seconds = base_overlap * overlap_factor 346 | 347 | # Adjust duration for playback speed 348 | actual_duration = duration / speed 349 | 350 | await asyncio.sleep(max(0.1, actual_duration - overlap_seconds)) 351 | reader.audio_queue.task_done() 352 | except asyncio.TimeoutError: 353 | if not reader.running: break 354 | continue 355 | except asyncio.CancelledError: break 356 | except asyncio.CancelledError: pass 357 | finally: 358 | for process in reader.playback_processes.copy(): 359 | try: 360 | if process.returncode is None: process.terminate() 361 | except (ProcessLookupError, AttributeError): pass -------------------------------------------------------------------------------- /VOICES.md: -------------------------------------------------------------------------------- 1 | # Lue - Voices and Languages Guide 2 | 3 | This document explains the speakers and languages included in the Edge and Kokoro TTS models, which are part of Lue’s default installation. 4 | 5 | *** 6 | 7 | ## Configuration 8 | 9 | To configure voices and languages, edit the `lue/config.py` file: 10 | 11 | ```python 12 | # Voice settings 13 | TTS_VOICES = { 14 | "edge": "en-US-JennyNeural", # Default Edge voice 15 | "kokoro": "af_heart", # Default Kokoro voice 16 | } 17 | 18 | # Language settings for TTS models 19 | TTS_LANGUAGE_CODES = { 20 | "kokoro": "a", # Language code for Kokoro TTS 21 | } 22 | ``` 23 | 24 | *** 25 | 26 | ## Supported Languages and Codes 27 | 28 | ### Edge Model Language Codes 29 | 30 | You don't need to specify language code for the Edge TTS model. Edge indicates the language in standard locale codes (e.g., `en-US`, `fr-FR`, `ja-JP`) within the speaker name. See the full list of Edge voices below. 31 | 32 | ### Kokoro Model Language Codes 33 | 34 | When using Kokoro, make sure the `lang_code` matches your selected voice. For more detailed information, refer to Kokoro TTS documentation: https://github.com/hexgrad/kokoro. 35 | 36 | | Language | Code | Notes | 37 | | :--- | :--- | :--- | 38 | | **American English** | `a` | Default language | 39 | | **British English** | `b` | | 40 | | **Spanish** | `e` | espeak-ng `es` fallback | 41 | | **French** | `f` | espeak-ng `fr-fr` fallback | 42 | | **Hindi** | `h` | espeak-ng `hi` fallback | 43 | | **Italian** | `i` | espeak-ng `it` fallback | 44 | | **Brazilian Portuguese**| `p` | espeak-ng `pt-br` fallback | 45 | | **Japanese** | `j` | Requires `pip install misaki[ja]` | 46 | | **Mandarin Chinese** | `z` | Requires `pip install misaki[zh]` | 47 | 48 | *** 49 | 50 | ## Available Voices by Language 51 | 52 | ### Edge Voices 53 | 54 | Edge TTS provides a wide variety of voices across many languages. Always include the full language code, country code, and voice name exactly as shown (e.g., en-US-JennyNeural): 55 | 56 | #### Afrikaans (South Africa) 57 | 58 | * af-ZA-AdriNeural (Female) 59 | * af-ZA-WillemNeural (Male) 60 | 61 | #### Albanian (Albania) 62 | 63 | * sq-AL-AnilaNeural (Female) 64 | * sq-AL-IlirNeural (Male) 65 | 66 | #### Amharic (Ethiopia) 67 | 68 | * am-ET-AmehaNeural (Male) 69 | * am-ET-MekdesNeural (Female) 70 | 71 | #### Arabic 72 | 73 | * ar-DZ-AminaNeural (Female) - Algeria 74 | * ar-DZ-IsmaelNeural (Male) - Algeria 75 | * ar-BH-AliNeural (Male) - Bahrain 76 | * ar-BH-LailaNeural (Female) - Bahrain 77 | * ar-EG-SalmaNeural (Female) - Egypt 78 | * ar-EG-ShakirNeural (Male) - Egypt 79 | * ar-IQ-BasselNeural (Male) - Iraq 80 | * ar-IQ-RanaNeural (Female) - Iraq 81 | * ar-JO-SanaNeural (Female) - Jordan 82 | * ar-JO-TaimNeural (Male) - Jordan 83 | * ar-KW-FahedNeural (Male) - Kuwait 84 | * ar-KW-NouraNeural (Female) - Kuwait 85 | * ar-LB-LaylaNeural (Female) - Lebanon 86 | * ar-LB-RamiNeural (Male) - Lebanon 87 | * ar-LY-ImanNeural (Female) - Libya 88 | * ar-LY-OmarNeural (Male) - Libya 89 | * ar-MA-JamalNeural (Male) - Morocco 90 | * ar-MA-MounaNeural (Female) - Morocco 91 | * ar-OM-AbdullahNeural (Male) - Oman 92 | * ar-OM-AyshaNeural (Female) - Oman 93 | * ar-QA-AmalNeural (Female) - Qatar 94 | * ar-QA-MoazNeural (Male) - Qatar 95 | * ar-SA-HamedNeural (Male) - Saudi Arabia 96 | * ar-SA-ZariyahNeural (Female) - Saudi Arabia 97 | * ar-SY-AmanyNeural (Female) - Syria 98 | * ar-SY-LaithNeural (Male) - Syria 99 | * ar-TN-HediNeural (Male) - Tunisia 100 | * ar-TN-ReemNeural (Female) - Tunisia 101 | * ar-AE-FatimaNeural (Female) - United Arab Emirates 102 | * ar-AE-HamdanNeural (Male) - United Arab Emirates 103 | * ar-YE-MaryamNeural (Female) - Yemen 104 | * ar-YE-SalehNeural (Male) - Yemen 105 | 106 | #### Azerbaijani (Azerbaijan) 107 | 108 | * az-AZ-BabekNeural (Male) 109 | * az-AZ-BanuNeural (Female) 110 | 111 | #### Bengali 112 | 113 | * bn-BD-NabanitaNeural (Female) - Bangladesh 114 | * bn-BD-PradeepNeural (Male) - Bangladesh 115 | * bn-IN-BashkarNeural (Male) - India 116 | * bn-IN-TanishaaNeural (Female) - India 117 | 118 | #### Bosnian (Bosnia and Herzegovina) 119 | 120 | * bs-BA-GoranNeural (Male) 121 | * bs-BA-VesnaNeural (Female) 122 | 123 | #### Bulgarian (Bulgaria) 124 | 125 | * bg-BG-BorislavNeural (Male) 126 | * bg-BG-KalinaNeural (Female) 127 | 128 | #### Burmese (Myanmar) 129 | 130 | * my-MM-NilarNeural (Female) 131 | * my-MM-ThihaNeural (Male) 132 | 133 | #### Catalan (Spain) 134 | 135 | * ca-ES-EnricNeural (Male) 136 | * ca-ES-JoanaNeural (Female) 137 | 138 | #### Chinese 139 | 140 | * zh-HK-HiuGaaiNeural (Female) - Hong Kong 141 | * zh-HK-HiuMaanNeural (Female) - Hong Kong 142 | * zh-HK-WanLungNeural (Male) - Hong Kong 143 | * zh-CN-XiaoxiaoNeural (Female) - Mandarin 144 | * zh-CN-XiaoyiNeural (Female) - Mandarin 145 | * zh-CN-YunjianNeural (Male) - Mandarin 146 | * zh-CN-YunxiNeural (Male) - Mandarin 147 | * zh-CN-YunxiaNeural (Male) - Mandarin 148 | * zh-CN-YunyangNeural (Male) - Mandarin 149 | * zh-CN-liaoning-XiaobeiNeural (Female) - Liaoning 150 | * zh-TW-HsiaoChenNeural (Female) - Taiwanese Mandarin 151 | * zh-TW-YunJheNeural (Male) - Taiwanese Mandarin 152 | * zh-TW-HsiaoYuNeural (Female) - Taiwanese Mandarin 153 | * zh-CN-shaanxi-XiaoniNeural (Female) - Shaanxi 154 | 155 | #### Croatian (Croatia) 156 | 157 | * hr-HR-GabrijelaNeural (Female) 158 | * hr-HR-SreckoNeural (Male) 159 | 160 | #### Czech (Czech Republic) 161 | 162 | * cs-CZ-AntoninNeural (Male) 163 | * cs-CZ-VlastaNeural (Female) 164 | 165 | #### Danish (Denmark) 166 | 167 | * da-DK-ChristelNeural (Female) 168 | * da-DK-JeppeNeural (Male) 169 | 170 | #### Dutch 171 | 172 | * nl-BE-ArnaudNeural (Male) - Belgium 173 | * nl-BE-DenaNeural (Female) - Belgium 174 | * nl-NL-ColetteNeural (Female) - Netherlands 175 | * nl-NL-FennaNeural (Female) - Netherlands 176 | * nl-NL-MaartenNeural (Male) - Netherlands 177 | 178 | #### English 179 | 180 | * en-AU-NatashaNeural (Female) - Australia 181 | * en-AU-WilliamNeural (Male) - Australia 182 | * en-CA-ClaraNeural (Female) - Canada 183 | * en-CA-LiamNeural (Male) - Canada 184 | * en-HK-SamNeural (Male) - Hong Kong 185 | * en-HK-YanNeural (Female) - Hong Kong 186 | * en-IN-NeerjaNeural (Female) - India 187 | * en-IN-PrabhatNeural (Male) - India 188 | * en-IE-ConnorNeural (Male) - Ireland 189 | * en-IE-EmilyNeural (Female) - Ireland 190 | * en-KE-AsiliaNeural (Female) - Kenya 191 | * en-KE-ChilembaNeural (Male) - Kenya 192 | * en-NZ-MitchellNeural (Male) - New Zealand 193 | * en-NZ-MollyNeural (Female) - New Zealand 194 | * en-NG-AbeoNeural (Male) - Nigeria 195 | * en-NG-EzinneNeural (Female) - Nigeria 196 | * en-PH-JamesNeural (Male) - Philippines 197 | * en-PH-RosaNeural (Female) - Philippines 198 | * en-SG-LunaNeural (Female) - Singapore 199 | * en-SG-WayneNeural (Male) - Singapore 200 | * en-ZA-LeahNeural (Female) - South Africa 201 | * en-ZA-LukeNeural (Male) - South Africa 202 | * en-TZ-ElimuNeural (Male) - Tanzania 203 | * en-TZ-ImaniNeural (Female) - Tanzania 204 | * en-GB-LibbyNeural (Female) - United Kingdom 205 | * en-GB-MaisieNeural (Female) - United Kingdom 206 | * en-GB-RyanNeural (Male) - United Kingdom 207 | * en-GB-SoniaNeural (Female) - United Kingdom 208 | * en-GB-ThomasNeural (Male) - United Kingdom 209 | * en-US-AriaNeural (Female) - United States 210 | * en-US-AnaNeural (Female) - United States 211 | * en-US-ChristopherNeural (Male) - United States 212 | * en-US-EricNeural (Male) - United States 213 | * en-US-GuyNeural (Male) - United States 214 | * **en-US-JennyNeural** (Female) - Default US English voice 215 | * en-US-MichelleNeural (Female) - United States 216 | * en-US-RogerNeural (Male) - United States 217 | * en-US-SteffanNeural (Male) - United States 218 | 219 | #### Estonian (Estonia) 220 | 221 | * et-EE-AnuNeural (Female) 222 | * et-EE-KertNeural (Male) 223 | 224 | #### Filipino (Philippines) 225 | 226 | * fil-PH-AngeloNeural (Male) 227 | * fil-PH-BlessicaNeural (Female) 228 | 229 | #### Finnish (Finland) 230 | 231 | * fi-FI-HarriNeural (Male) 232 | * fi-FI-NooraNeural (Female) 233 | 234 | #### French 235 | 236 | * fr-BE-CharlineNeural (Female) - Belgium 237 | * fr-BE-GerardNeural (Male) - Belgium 238 | * fr-CA-AntoineNeural (Male) - Canada 239 | * fr-CA-JeanNeural (Male) - Canada 240 | * fr-CA-SylvieNeural (Female) - Canada 241 | * fr-FR-DeniseNeural (Female) - France 242 | * fr-FR-EloiseNeural (Female) - France 243 | * fr-FR-HenriNeural (Male) - France 244 | * fr-CH-ArianeNeural (Female) - Switzerland 245 | * fr-CH-FabriceNeural (Male) - Switzerland 246 | 247 | #### Galician (Spain) 248 | 249 | * gl-ES-RoiNeural (Male) 250 | * gl-ES-SabelaNeural (Female) 251 | 252 | #### Georgian (Georgia) 253 | 254 | * ka-GE-EkaNeural (Female) 255 | * ka-GE-GiorgiNeural (Male) 256 | 257 | #### German 258 | 259 | * de-AT-IngridNeural (Female) - Austria 260 | * de-AT-JonasNeural (Male) - Austria 261 | * de-DE-AmalaNeural (Female) - Germany 262 | * de-DE-ConradNeural (Male) - Germany 263 | * de-DE-KatjaNeural (Female) - Germany 264 | * de-DE-KillianNeural (Male) - Germany 265 | * de-CH-JanNeural (Male) - Switzerland 266 | * de-CH-LeniNeural (Female) - Switzerland 267 | 268 | #### Greek (Greece) 269 | 270 | * el-GR-AthinaNeural (Female) 271 | * el-GR-NestorasNeural (Male) 272 | 273 | #### Gujarati (India) 274 | 275 | * gu-IN-DhwaniNeural (Female) 276 | * gu-IN-NiranjanNeural (Male) 277 | 278 | #### Hebrew (Israel) 279 | 280 | * he-IL-AvriNeural (Male) 281 | * he-IL-HilaNeural (Female) 282 | 283 | #### Hindi (India) 284 | 285 | * hi-IN-MadhurNeural (Male) 286 | * hi-IN-SwaraNeural (Female) 287 | 288 | #### Hungarian (Hungary) 289 | 290 | * hu-HU-NoemiNeural (Female) 291 | * hu-HU-TamasNeural (Male) 292 | 293 | #### Icelandic (Iceland) 294 | 295 | * is-IS-GudrunNeural (Female) 296 | * is-IS-GunnarNeural (Male) 297 | 298 | #### Indonesian (Indonesia) 299 | 300 | * id-ID-ArdiNeural (Male) 301 | * id-ID-GadisNeural (Female) 302 | 303 | #### Irish (Ireland) 304 | 305 | * ga-IE-ColmNeural (Male) 306 | * ga-IE-OrlaNeural (Female) 307 | 308 | #### Italian (Italy) 309 | 310 | * it-IT-DiegoNeural (Male) 311 | * it-IT-ElsaNeural (Female) 312 | * it-IT-IsabellaNeural (Female) 313 | 314 | #### Japanese (Japan) 315 | 316 | * ja-JP-KeitaNeural (Male) 317 | * ja-JP-NanamiNeural (Female) 318 | 319 | #### Javanese (Indonesia) 320 | 321 | * jv-ID-DimasNeural (Male) 322 | * jv-ID-SitiNeural (Female) 323 | 324 | #### Kannada (India) 325 | 326 | * kn-IN-GaganNeural (Male) 327 | * kn-IN-SapnaNeural (Female) 328 | 329 | #### Kazakh (Kazakhstan) 330 | 331 | * kk-KZ-AigulNeural (Female) 332 | * kk-KZ-DauletNeural (Male) 333 | 334 | #### Khmer (Cambodia) 335 | 336 | * km-KH-PisethNeural (Male) 337 | * km-KH-SreymomNeural (Female) 338 | 339 | #### Korean (Korea) 340 | 341 | * ko-KR-InJoonNeural (Male) 342 | * ko-KR-SunHiNeural (Female) 343 | 344 | #### Lao (Laos) 345 | 346 | * lo-LA-ChanthavongNeural (Male) 347 | * lo-LA-KeomanyNeural (Female) 348 | 349 | #### Latvian (Latvia) 350 | 351 | * lv-LV-EveritaNeural (Female) 352 | * lv-LV-NilsNeural (Male) 353 | 354 | #### Lithuanian (Lithuania) 355 | 356 | * lt-LT-LeonasNeural (Male) 357 | * lt-LT-OnaNeural (Female) 358 | 359 | #### Macedonian (North Macedonia) 360 | 361 | * mk-MK-AleksandarNeural (Male) 362 | * mk-MK-MarijaNeural (Female) 363 | 364 | #### Malay (Malaysia) 365 | 366 | * ms-MY-OsmanNeural (Male) 367 | * ms-MY-YasminNeural (Female) 368 | 369 | #### Malayalam (India) 370 | 371 | * ml-IN-MidhunNeural (Male) 372 | * ml-IN-SobhanaNeural (Female) 373 | 374 | #### Maltese (Malta) 375 | 376 | * mt-MT-GraceNeural (Female) 377 | * mt-MT-JosephNeural (Male) 378 | 379 | #### Marathi (India) 380 | 381 | * mr-IN-AarohiNeural (Female) 382 | * mr-IN-ManoharNeural (Male) 383 | 384 | #### Mongolian (Mongolia) 385 | 386 | * mn-MN-BataaNeural (Male) 387 | * mn-MN-YesuiNeural (Female) 388 | 389 | #### Nepali (Nepal) 390 | 391 | * ne-NP-HemkalaNeural (Female) 392 | * ne-NP-SagarNeural (Male) 393 | 394 | #### Norwegian (Bokmål, Norway) 395 | 396 | * nb-NO-FinnNeural (Male) 397 | * nb-NO-PernilleNeural (Female) 398 | 399 | #### Pashto (Afghanistan) 400 | 401 | * ps-AF-GulNawazNeural (Male) 402 | * ps-AF-LatifaNeural (Female) 403 | 404 | #### Persian (Iran) 405 | 406 | * fa-IR-DilaraNeural (Female) 407 | * fa-IR-FaridNeural (Male) 408 | 409 | #### Polish (Poland) 410 | 411 | * pl-PL-MarekNeural (Male) 412 | * pl-PL-ZofiaNeural (Female) 413 | 414 | #### Portuguese 415 | 416 | * pt-BR-AntonioNeural (Male) - Brazil 417 | * pt-BR-FranciscaNeural (Female) - Brazil 418 | * pt-PT-DuarteNeural (Male) - Portugal 419 | * pt-PT-RaquelNeural (Female) - Portugal 420 | 421 | #### Romanian (Romania) 422 | 423 | * ro-RO-AlinaNeural (Female) 424 | * ro-RO-EmilNeural (Male) 425 | 426 | #### Russian (Russia) 427 | 428 | * ru-RU-DmitryNeural (Male) 429 | * ru-RU-SvetlanaNeural (Female) 430 | 431 | #### Serbian (Serbia) 432 | 433 | * sr-RS-NicholasNeural (Male) 434 | * sr-RS-SophieNeural (Female) 435 | 436 | #### Sinhala (Sri Lanka) 437 | 438 | * si-LK-SameeraNeural (Male) 439 | * si-LK-ThiliniNeural (Female) 440 | 441 | #### Slovak (Slovakia) 442 | 443 | * sk-SK-LukasNeural (Male) 444 | * sk-SK-ViktoriaNeural (Female) 445 | 446 | #### Slovenian (Slovenia) 447 | 448 | * sl-SI-PetraNeural (Female) 449 | * sl-SI-RokNeural (Male) 450 | 451 | #### Somali (Somalia) 452 | 453 | * so-SO-MuuseNeural (Male) 454 | * so-SO-UbaxNeural (Female) 455 | 456 | #### Spanish 457 | 458 | * es-AR-ElenaNeural (Female) - Argentina 459 | * es-AR-TomasNeural (Male) - Argentina 460 | * es-BO-MarceloNeural (Male) - Bolivia 461 | * es-BO-SofiaNeural (Female) - Bolivia 462 | * es-CL-CatalinaNeural (Female) - Chile 463 | * es-CL-LorenzoNeural (Male) - Chile 464 | * es-CO-GonzaloNeural (Male) - Colombia 465 | * es-CO-SalomeNeural (Female) - Colombia 466 | * es-CR-JuanNeural (Male) - Costa Rica 467 | * es-CR-MariaNeural (Female) - Costa Rica 468 | * es-CU-BelkysNeural (Female) - Cuba 469 | * es-CU-ManuelNeural (Male) - Cuba 470 | * es-DO-EmilioNeural (Male) - Dominican Republic 471 | * es-DO-RamonaNeural (Female) - Dominican Republic 472 | * es-EC-AndreaNeural (Female) - Ecuador 473 | * es-EC-LuisNeural (Male) - Ecuador 474 | * es-SV-LorenaNeural (Female) - El Salvador 475 | * es-SV-RodrigoNeural (Male) - El Salvador 476 | * es-GQ-JavierNeural (Male) - Equatorial Guinea 477 | * es-GQ-TeresaNeural (Female) - Equatorial Guinea 478 | * es-GT-AndresNeural (Male) - Guatemala 479 | * es-GT-MartaNeural (Female) - Guatemala 480 | * es-HN-CarlosNeural (Male) - Honduras 481 | * es-HN-KarlaNeural (Female) - Honduras 482 | * es-MX-DaliaNeural (Female) - Mexico 483 | * es-MX-JorgeNeural (Male) - Mexico 484 | * es-NI-FedericoNeural (Male) - Nicaragua 485 | * es-NI-YolandaNeural (Female) - Nicaragua 486 | * es-PA-MargaritaNeural (Female) - Panama 487 | * es-PA-RobertoNeural (Male) - Panama 488 | * es-PY-MarioNeural (Male) - Paraguay 489 | * es-PY-TaniaNeural (Female) - Paraguay 490 | * es-PE-AlexNeural (Male) - Peru 491 | * es-PE-CamilaNeural (Female) - Peru 492 | * es-PR-KarinaNeural (Female) - Puerto Rico 493 | * es-PR-VictorNeural (Male) - Puerto Rico 494 | * es-ES-AlvaroNeural (Male) - Spain 495 | * es-ES-ElviraNeural (Female) - Spain 496 | * es-US-AlonsoNeural (Male) - United States 497 | * es-US-PalomaNeural (Female) - United States 498 | * es-UY-MateoNeural (Male) - Uruguay 499 | * es-UY-ValentinaNeural (Female) - Uruguay 500 | * es-VE-PaolaNeural (Female) - Venezuela 501 | * es-VE-SebastianNeural (Male) - Venezuela 502 | 503 | #### Sundanese (Indonesia) 504 | 505 | * su-ID-JajangNeural (Male) 506 | * su-ID-TutiNeural (Female) 507 | 508 | #### Swahili 509 | 510 | * sw-KE-RafikiNeural (Male) - Kenya 511 | * sw-KE-ZuriNeural (Female) - Kenya 512 | * sw-TZ-DaudiNeural (Male) - Tanzania 513 | * sw-TZ-RehemaNeural (Female) - Tanzania 514 | 515 | #### Swedish (Sweden) 516 | 517 | * sv-SE-MattiasNeural (Male) 518 | * sv-SE-SofieNeural (Female) 519 | 520 | #### Tamil 521 | 522 | * ta-IN-PallaviNeural (Female) - India 523 | * ta-IN-ValluvarNeural (Male) - India 524 | * ta-MY-KaniNeural (Female) - Malaysia 525 | * ta-MY-SuryaNeural (Male) - Malaysia 526 | * ta-SG-AnbuNeural (Male) - Singapore 527 | * ta-SG-VenbaNeural (Female) - Singapore 528 | * ta-LK-KumarNeural (Male) - Sri Lanka 529 | * ta-LK-SaranyaNeural (Female) - Sri Lanka 530 | 531 | #### Telugu (India) 532 | 533 | * te-IN-MohanNeural (Male) 534 | * te-IN-ShrutiNeural (Female) 535 | 536 | #### Thai (Thailand) 537 | 538 | * th-TH-NiwatNeural (Male) 539 | * th-TH-PremwadeeNeural (Female) 540 | 541 | #### Turkish (Turkey) 542 | 543 | * tr-TR-AhmetNeural (Male) 544 | * tr-TR-EmelNeural (Female) 545 | 546 | #### Ukrainian (Ukraine) 547 | 548 | * uk-UA-OstapNeural (Male) 549 | * uk-UA-PolinaNeural (Female) 550 | 551 | #### Urdu 552 | 553 | * ur-IN-GulNeural (Female) - India 554 | * ur-IN-SalmanNeural (Male) - India 555 | * ur-PK-AsadNeural (Male) - Pakistan 556 | * ur-PK-UzmaNeural (Female) - Pakistan 557 | 558 | #### Uzbek (Uzbekistan) 559 | 560 | * uz-UZ-MadinaNeural (Female) 561 | * uz-UZ-SardorNeural (Male) 562 | 563 | #### Vietnamese (Vietnam) 564 | 565 | * vi-VN-HoaiMyNeural (Female) 566 | * vi-VN-NamMinhNeural (Male) 567 | 568 | #### Welsh (United Kingdom) 569 | 570 | * cy-GB-AledNeural (Male) 571 | * cy-GB-NiaNeural (Female) 572 | 573 | #### Zulu (South Africa) 574 | 575 | * zu-ZA-ThandoNeural (Female) 576 | * zu-ZA-ThembaNeural (Male) 577 | 578 | *** 579 | 580 | ### Kokoro Voices 581 | 582 | #### American English (`lang_code='a'`) 583 | 584 | * **af_heart** (Female) 585 | * af_alloy (Female) 586 | * af_aoede (Female) 587 | * af_bella (Female) 588 | * af_jessica (Female) 589 | * af_kore (Female) 590 | * af_nicole (Female) 591 | * af_nova (Female) 592 | * af_river (Female) 593 | * af_sarah (Female) 594 | * af_sky (Female) 595 | * am_adam (Male) 596 | * am_echo (Male) 597 | * am_eric (Male) 598 | * am_fenrir (Male) 599 | * am_liam (Male) 600 | * am_michael (Male) 601 | * am_onyx (Male) 602 | * am_puck (Male) 603 | * am_santa (Male) 604 | 605 | #### British English (`lang_code='b'`) 606 | 607 | * bf_alice (Female) 608 | * bf_emma (Female) 609 | * bf_isabella (Female) 610 | * bf_lily (Female) 611 | * bm_daniel (Male) 612 | * bm_fable (Male) 613 | * bm_george (Male) 614 | * bm_lewis (Male) 615 | 616 | #### Japanese (`lang_code='j'`) 617 | 618 | * jf_alpha (Female) 619 | * jf_gongitsune (Female) 620 | * jf_nezumi (Female) 621 | * jf_tebukuro (Female) 622 | * jm_kumo (Male) 623 | 624 | #### Mandarin Chinese (`lang_code='z'`) 625 | 626 | * zf_xiaobei (Female) 627 | * zf_xiaoni (Female) 628 | * zf_xiaoxiao (Female) 629 | * zf_xiaoyi (Female) 630 | * zm_yunjian (Male) 631 | * zm_yunxi (Male) 632 | * zm_yunxia (Male) 633 | * zm_yunyang (Male) 634 | 635 | #### Spanish (`lang_code='e'`) 636 | 637 | * ef_dora (Female) 638 | * em_alex (Male) 639 | * em_santa (Male) 640 | 641 | #### French (`lang_code='f'`) 642 | 643 | * ff_siwis (Female) 644 | 645 | #### Hindi (`lang_code='h'`) 646 | 647 | * hf_alpha (Female) 648 | * hf_beta (Female) 649 | * hm_omega (Male) 650 | * hm_psi (Male) 651 | 652 | #### Italian (`lang_code='i'`) 653 | 654 | * if_sara (Female) 655 | * im_nicola (Male) 656 | 657 | #### Brazilian Portuguese (`lang_code='p'`) 658 | 659 | * pf_dora (Female) 660 | * pm_alex (Male) 661 | * pm_santa (Male) 662 | -------------------------------------------------------------------------------- /lue/timing_calculator.py: -------------------------------------------------------------------------------- 1 | """ 2 | Word-level timing calculation module for the Lue eBook reader. 3 | """ 4 | 5 | import logging 6 | import re 7 | import string 8 | from typing import List, Tuple, Optional, Dict, Any 9 | 10 | def _sanitize_word(word: str) -> str: 11 | """ 12 | Sanitize a word by stripping all non-alphanumeric characters and converting to lowercase. 13 | 14 | This function is used for case-insensitive word comparison by removing punctuation 15 | and other special characters, leaving only letters and numbers. 16 | 17 | Args: 18 | word: The word to sanitize 19 | 20 | Returns: 21 | Sanitized word containing only lowercase alphanumeric characters 22 | """ 23 | if not word: 24 | return "" 25 | 26 | # Strip all non-alphanumeric characters 27 | sanitized = re.sub(r'[^a-zA-Z0-9]', '', word) 28 | 29 | # Convert to lowercase for case-insensitive comparison 30 | return sanitized.lower() 31 | 32 | 33 | def _get_highlightable_words(text: str) -> list[str]: 34 | """ 35 | Get list of words that should be considered for timing. 36 | 37 | This function filters out tokens that contain only punctuation/non-alphanumeric 38 | characters, which should not be counted as words for timing purposes. 39 | Strips punctuation (including commas from em dash replacement) for counting. 40 | 41 | Args: 42 | text: The text to process 43 | 44 | Returns: 45 | List of cleaned words that should be timed 46 | """ 47 | # Split on whitespace to get tokens 48 | tokens = text.split() 49 | 50 | # Strip punctuation from tokens and filter out pure punctuation 51 | words = [] 52 | for token in tokens: 53 | cleaned = token.strip(string.punctuation) 54 | if cleaned: # Only include non-empty cleaned tokens 55 | words.append(cleaned) 56 | 57 | return words 58 | 59 | 60 | def _extract_core_word(token: str) -> str: 61 | """ 62 | Extract the core word from a token by removing surrounding punctuation. 63 | 64 | This function is more robust than simple strip() as it handles nested 65 | punctuation and preserves internal punctuation like contractions. 66 | 67 | Args: 68 | token: The token to process 69 | 70 | Returns: 71 | The core word without surrounding punctuation 72 | """ 73 | if not token: 74 | return token 75 | 76 | # Remove leading punctuation 77 | start = 0 78 | while start < len(token) and not token[start].isalnum(): 79 | start += 1 80 | 81 | # Remove trailing punctuation 82 | end = len(token) - 1 83 | while end >= start and not token[end].isalnum(): 84 | end -= 1 85 | 86 | if start <= end: 87 | return token[start:end + 1] 88 | else: 89 | return "" 90 | 91 | 92 | def create_word_mapping(original_words: List[str], tts_word_timings: List[Tuple[str, float, float]]) -> Optional[List[int]]: 93 | """ 94 | Create a mapping from original word indices to TTS word timing indices. 95 | This handles cases where TTS combines words or processes punctuation differently. 96 | 97 | Uses sanitized word comparison with fuzzy matching to handle: 98 | - Punctuation differences between original and TTS text 99 | - Case differences 100 | - Word combining/splitting by TTS engines 101 | - Punctuation-only tokens 102 | 103 | Args: 104 | original_words: List of words from the original text 105 | tts_word_timings: List of (word, start_time, end_time) tuples from TTS 106 | 107 | Returns: 108 | List where index i contains the TTS timing index for original word i, 109 | or None if no valid mapping can be created. 110 | """ 111 | # Handle edge cases: empty inputs 112 | if not original_words or not tts_word_timings: 113 | logging.debug("create_word_mapping: Empty input - original_words or tts_word_timings is empty") 114 | return None 115 | 116 | # Extract just the text from TTS timings 117 | tts_words = [word for word, _, _ in tts_word_timings] 118 | 119 | # Sanitize both original and TTS words for comparison 120 | orig_sanitized = [_sanitize_word(word) for word in original_words] 121 | tts_sanitized = [_sanitize_word(word) for word in tts_words] 122 | 123 | # If counts match and sanitized words match, create simple 1:1 mapping 124 | if len(original_words) == len(tts_words): 125 | # Check if sanitized versions match 126 | if orig_sanitized == tts_sanitized: 127 | logging.debug(f"create_word_mapping: Perfect 1:1 match with {len(original_words)} words") 128 | return list(range(len(original_words))) 129 | 130 | # Create enhanced mapping algorithm with fuzzy matching 131 | mapping = [] 132 | tts_index = 0 133 | 134 | logging.debug(f"create_word_mapping: Mapping {len(original_words)} original words to {len(tts_words)} TTS words") 135 | 136 | for orig_index, orig_word in enumerate(original_words): 137 | # Handle edge case: exhausted TTS words 138 | if tts_index >= len(tts_words): 139 | # Map remaining original words to the last TTS word 140 | last_tts_index = max(0, len(tts_words) - 1) 141 | mapping.append(last_tts_index) 142 | logging.debug(f"create_word_mapping: Word {orig_index} '{orig_word}' -> TTS {last_tts_index} (exhausted TTS words)") 143 | continue 144 | 145 | orig_sanitized_word = orig_sanitized[orig_index] 146 | 147 | # Handle punctuation-only tokens by mapping to previous word 148 | if not orig_sanitized_word: 149 | # Map punctuation to the previous word's timing, or first TTS word if this is the first original word 150 | if mapping: 151 | prev_mapping = mapping[-1] 152 | mapping.append(prev_mapping) 153 | logging.debug(f"create_word_mapping: Word {orig_index} '{orig_word}' (punctuation-only) -> TTS {prev_mapping} (previous)") 154 | else: 155 | mapping.append(0) 156 | logging.debug(f"create_word_mapping: Word {orig_index} '{orig_word}' (punctuation-only) -> TTS 0 (first)") 157 | continue 158 | 159 | # Find the best matching TTS word using fuzzy matching with scoring 160 | best_match_index = None 161 | best_match_score = 0 162 | 163 | # Look ahead up to 5 positions to find best TTS word match 164 | search_range = min(len(tts_words), tts_index + 5) 165 | 166 | for search_idx in range(tts_index, search_range): 167 | tts_sanitized_word = tts_sanitized[search_idx] 168 | 169 | # Skip empty TTS words (shouldn't happen but handle gracefully) 170 | if not tts_sanitized_word: 171 | continue 172 | 173 | # Calculate match score using fuzzy matching 174 | score = 0 175 | 176 | # Perfect match: sanitized words are identical (score = 100) 177 | if orig_sanitized_word == tts_sanitized_word: 178 | score = 100 179 | # Original word contained in TTS word (score = 80) 180 | elif orig_sanitized_word in tts_sanitized_word: 181 | score = 80 182 | # TTS word contained in original word (score = 60) 183 | elif tts_sanitized_word in orig_sanitized_word: 184 | score = 60 185 | # Similar words using heuristic matching (score = 40) 186 | elif _words_similar(orig_sanitized_word, tts_sanitized_word): 187 | score = 40 188 | 189 | # Update best match if this score is higher 190 | if score > best_match_score: 191 | best_match_score = score 192 | best_match_index = search_idx 193 | 194 | # If we found a perfect match, no need to search further 195 | if score == 100: 196 | break 197 | 198 | # Handle edge case: no matches found 199 | if best_match_index is None or best_match_score == 0: 200 | # No good match found, use current TTS index as fallback 201 | mapping.append(tts_index) 202 | logging.debug(f"create_word_mapping: Word {orig_index} '{orig_word}' -> TTS {tts_index} (no match, fallback)") 203 | tts_index += 1 204 | else: 205 | # Found a match, use it 206 | mapping.append(best_match_index) 207 | logging.debug(f"create_word_mapping: Word {orig_index} '{orig_word}' -> TTS {best_match_index} '{tts_words[best_match_index]}' (score={best_match_score})") 208 | 209 | # Advance tts_index if we found a good match and it's not too far ahead 210 | # This prevents skipping too many TTS words at once 211 | if best_match_index <= tts_index + 2: 212 | tts_index = best_match_index + 1 213 | 214 | # Handle edge case: mismatched counts - log warning 215 | if len(original_words) != len(tts_words): 216 | logging.debug(f"create_word_mapping: Word count mismatch - {len(original_words)} original vs {len(tts_words)} TTS") 217 | 218 | return mapping 219 | 220 | 221 | def _words_similar(word1: str, word2: str) -> bool: 222 | """ 223 | Check if two words are similar (for handling slight differences in tokenization). 224 | 225 | Args: 226 | word1: First word to compare 227 | word2: Second word to compare 228 | 229 | Returns: 230 | True if words are similar, False otherwise 231 | """ 232 | if not word1 or not word2: 233 | return False 234 | 235 | # Check if one word is a substring of the other with small differences 236 | if len(word1) >= 3 and len(word2) >= 3: 237 | if word1 in word2 or word2 in word1: 238 | return True 239 | 240 | # Check for common prefixes/suffixes 241 | if len(word1) >= 4 and len(word2) >= 4: 242 | if (word1[:3] == word2[:3] and abs(len(word1) - len(word2)) <= 2): 243 | return True 244 | 245 | return False 246 | 247 | 248 | def adjust_word_timings_for_continuity(word_timings: List[Tuple[str, float, float]]) -> List[Tuple[str, float, float]]: 249 | """ 250 | Adjust word timings to ensure continuity and handle timing inconsistencies. 251 | 252 | Args: 253 | word_timings: List of (word, start_time, end_time) tuples 254 | 255 | Returns: 256 | Adjusted list of (word, start_time, end_time) tuples 257 | """ 258 | if len(word_timings) <= 1: 259 | return word_timings 260 | 261 | adjusted_word_timings = [] 262 | 263 | # First pass: fix any obviously broken timings 264 | cleaned_timings = [] 265 | for i, (word, start_time, end_time) in enumerate(word_timings): 266 | # Skip entries with None values 267 | if start_time is None or end_time is None: 268 | cleaned_timings.append((word, start_time, end_time)) 269 | continue 270 | 271 | # Fix backwards timings 272 | if end_time < start_time: 273 | # Swap them or use a small duration 274 | if start_time > 0: 275 | end_time = start_time + 0.1 276 | else: 277 | start_time, end_time = end_time, start_time + 0.1 278 | 279 | # Ensure minimum duration 280 | if end_time - start_time < 0.05: # Minimum 50ms 281 | end_time = start_time + 0.05 282 | 283 | cleaned_timings.append((word, start_time, end_time)) 284 | 285 | # Second pass: ensure continuity 286 | for i in range(len(cleaned_timings)): 287 | word, start_time, end_time = cleaned_timings[i] 288 | 289 | # Skip entries with None values 290 | if start_time is None or end_time is None: 291 | adjusted_word_timings.append((word, start_time, end_time)) 292 | continue 293 | 294 | # For all words except the last one, adjust end time for continuity 295 | if i < len(cleaned_timings) - 1: 296 | next_word, next_start_time, next_end_time = cleaned_timings[i + 1] 297 | 298 | # Only adjust if next start time is valid 299 | if next_start_time is not None: 300 | # If there's a gap, extend current word to fill it 301 | if next_start_time > end_time: 302 | adjusted_end_time = next_start_time 303 | # If there's overlap, split the difference 304 | elif next_start_time < end_time: 305 | adjusted_end_time = (end_time + next_start_time) / 2 306 | else: 307 | adjusted_end_time = end_time 308 | else: 309 | adjusted_end_time = end_time 310 | else: 311 | # For the last word, keep the original end time 312 | adjusted_end_time = end_time 313 | 314 | adjusted_word_timings.append((word, start_time, adjusted_end_time)) 315 | 316 | return adjusted_word_timings 317 | 318 | 319 | def calculate_speech_duration(word_timings: List[Tuple[str, float, float]]) -> float: 320 | """ 321 | Calculate the total speech duration from word timings. 322 | 323 | Args: 324 | word_timings: List of (word, start_time, end_time) tuples 325 | 326 | Returns: 327 | Speech duration in seconds 328 | """ 329 | if not word_timings: 330 | return 0.0 331 | 332 | return max([end for _, _, end in word_timings]) 333 | 334 | 335 | def estimate_word_timings_from_duration(text: str, total_duration: float) -> List[Tuple[str, float, float]]: 336 | """ 337 | Estimate word timings based on word count and total duration. 338 | This is a fallback when TTS doesn't provide precise timing information. 339 | 340 | Args: 341 | text: The text that was spoken 342 | total_duration: Total duration of the audio in seconds 343 | 344 | Returns: 345 | List of (word, start_time, end_time) tuples 346 | """ 347 | # Use the improved word filtering function 348 | words = _get_highlightable_words(text) 349 | if not words: 350 | return [] 351 | 352 | # If we couldn't get duration, estimate 0.3 seconds per word 353 | if total_duration is None or total_duration <= 0: 354 | total_duration = len(words) * 0.3 355 | 356 | time_per_word = total_duration / len(words) 357 | word_timings = [] 358 | 359 | for i, word in enumerate(words): 360 | start_time = i * time_per_word 361 | end_time = (i + 1) * time_per_word 362 | word_timings.append((word, start_time, end_time)) 363 | 364 | return word_timings 365 | 366 | 367 | def process_tts_timing_data( 368 | original_text: str, 369 | raw_word_timings: List[Tuple[str, float, float]], 370 | total_duration: Optional[float] = None 371 | ) -> Dict[str, Any]: 372 | """ 373 | Process raw timing data from TTS into a standardized format with all necessary 374 | calculations and adjustments applied. 375 | 376 | Args: 377 | original_text: The original text that was spoken 378 | raw_word_timings: Raw word timings from TTS engine 379 | total_duration: Total audio duration (optional, will be calculated if not provided) 380 | 381 | Returns: 382 | Dictionary containing: 383 | - word_timings: Adjusted word timings 384 | - speech_duration: Duration of speech content 385 | - total_duration: Total audio duration 386 | - word_mapping: Mapping from original words to TTS timings 387 | """ 388 | try: 389 | # If no raw timings provided, estimate from duration 390 | if not raw_word_timings: 391 | if total_duration is None: 392 | logging.warning("No timing data and no duration provided, using fallback estimation") 393 | total_duration = len(original_text.split()) * 0.3 394 | 395 | word_timings = estimate_word_timings_from_duration(original_text, total_duration) 396 | speech_duration = total_duration 397 | else: 398 | # Log raw timing data for debugging 399 | logging.debug(f"Processing {len(raw_word_timings)} raw timing entries for text: '{original_text[:50]}...'") 400 | 401 | # Adjust raw timings for continuity 402 | word_timings = adjust_word_timings_for_continuity(raw_word_timings) 403 | speech_duration = calculate_speech_duration(word_timings) 404 | 405 | # Create word mapping using the improved word filtering 406 | original_words = _get_highlightable_words(original_text) 407 | word_mapping = create_word_mapping(original_words, word_timings) 408 | 409 | # Log mapping information for debugging 410 | if word_mapping: 411 | logging.debug(f"Created word mapping: {len(original_words)} original words -> {len(word_timings)} TTS timings") 412 | if len(original_words) != len(word_timings): 413 | logging.debug(f"Word count mismatch - Original: {original_words}, TTS: {[w for w, _, _ in word_timings]}") 414 | 415 | # Use provided total_duration or fall back to speech_duration 416 | final_total_duration = total_duration if total_duration is not None else speech_duration 417 | 418 | return { 419 | "word_timings": word_timings, 420 | "speech_duration": speech_duration, 421 | "total_duration": final_total_duration, 422 | "word_mapping": word_mapping 423 | } 424 | 425 | except Exception as e: 426 | logging.error(f"Error processing TTS timing data: {e}", exc_info=True) 427 | # Return fallback data 428 | # Use the improved word filtering function 429 | fallback_words = _get_highlightable_words(original_text) 430 | fallback_duration = len(fallback_words) * 0.3 431 | fallback_timings = estimate_word_timings_from_duration(original_text, fallback_duration) 432 | 433 | return { 434 | "word_timings": fallback_timings, 435 | "speech_duration": fallback_duration, 436 | "total_duration": fallback_duration, 437 | "word_mapping": create_word_mapping(fallback_words, fallback_timings) 438 | } 439 | 440 | 441 | def validate_timing_data(timing_data: Dict[str, Any]) -> bool: 442 | """ 443 | Validate that timing data contains all required fields and is properly formatted. 444 | 445 | Args: 446 | timing_data: Dictionary containing timing information 447 | 448 | Returns: 449 | True if valid, False otherwise 450 | """ 451 | required_fields = ["word_timings", "speech_duration", "total_duration"] 452 | 453 | for field in required_fields: 454 | if field not in timing_data: 455 | return False 456 | 457 | word_timings = timing_data["word_timings"] 458 | if not isinstance(word_timings, list): 459 | return False 460 | 461 | # Check that each timing entry is properly formatted 462 | for timing in word_timings: 463 | if not isinstance(timing, tuple) or len(timing) != 3: 464 | return False 465 | word, start_time, end_time = timing 466 | if not isinstance(word, str): 467 | return False 468 | # Allow None values for start_time and end_time, but if they're not None, they should be numbers 469 | if start_time is not None and not isinstance(start_time, (int, float)): 470 | return False 471 | if end_time is not None and not isinstance(end_time, (int, float)): 472 | return False 473 | # If both are numbers, check the relationship 474 | if isinstance(start_time, (int, float)) and isinstance(end_time, (int, float)) and start_time < 0: 475 | return False 476 | if (isinstance(start_time, (int, float)) and isinstance(end_time, (int, float)) and 477 | end_time < start_time): 478 | return False 479 | 480 | return True 481 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | 635 | Copyright (C) 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | Copyright (C) 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | --------------------------------------------------------------------------------