├── .gitignore ├── LICENSE ├── README.md ├── app.py ├── audio_output └── audio_0.wav └── requirements.txt /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/#use-with-ide 110 | .pdm.toml 111 | 112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 113 | __pypackages__/ 114 | 115 | # Celery stuff 116 | celerybeat-schedule 117 | celerybeat.pid 118 | 119 | # SageMath parsed files 120 | *.sage.py 121 | 122 | # Environments 123 | .env 124 | .venv 125 | env/ 126 | venv/ 127 | ENV/ 128 | env.bak/ 129 | venv.bak/ 130 | 131 | # Spyder project settings 132 | .spyderproject 133 | .spyproject 134 | 135 | # Rope project settings 136 | .ropeproject 137 | 138 | # mkdocs documentation 139 | /site 140 | 141 | # mypy 142 | .mypy_cache/ 143 | .dmypy.json 144 | dmypy.json 145 | 146 | # Pyre type checker 147 | .pyre/ 148 | 149 | # pytype static type analyzer 150 | .pytype/ 151 | 152 | # Cython debug symbols 153 | cython_debug/ 154 | 155 | # PyCharm 156 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 157 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 158 | # and can be added to the global gitignore or merged into this file. For a more nuclear 159 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 160 | #.idea/ 161 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2023 AI Anytime 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Text-to-Music-Generation-App 2 | Text to Music Generation App built using Meta's Audiocraft library. It is a Streamlit application utilises Music Gen small model. 3 | -------------------------------------------------------------------------------- /app.py: -------------------------------------------------------------------------------- 1 | from audiocraft.models import MusicGen 2 | import streamlit as st 3 | import torch 4 | import torchaudio 5 | import os 6 | import numpy as np 7 | import base64 8 | 9 | @st.cache_resource 10 | def load_model(): 11 | model = MusicGen.get_pretrained('facebook/musicgen-small') 12 | return model 13 | 14 | def generate_music_tensors(description, duration: int): 15 | print("Description: ", description) 16 | print("Duration: ", duration) 17 | model = load_model() 18 | 19 | model.set_generation_params( 20 | use_sampling=True, 21 | top_k=250, 22 | duration=duration 23 | ) 24 | 25 | output = model.generate( 26 | descriptions=[description], 27 | progress=True, 28 | return_tokens=True 29 | ) 30 | 31 | return output[0] 32 | 33 | 34 | def save_audio(samples: torch.Tensor): 35 | """Renders an audio player for the given audio samples and saves them to a local directory. 36 | 37 | Args: 38 | samples (torch.Tensor): a Tensor of decoded audio samples 39 | with shapes [B, C, T] or [C, T] 40 | sample_rate (int): sample rate audio should be displayed with. 41 | save_path (str): path to the directory where audio should be saved. 42 | """ 43 | 44 | print("Samples (inside function): ", samples) 45 | sample_rate = 32000 46 | save_path = "audio_output/" 47 | assert samples.dim() == 2 or samples.dim() == 3 48 | 49 | samples = samples.detach().cpu() 50 | if samples.dim() == 2: 51 | samples = samples[None, ...] 52 | 53 | for idx, audio in enumerate(samples): 54 | audio_path = os.path.join(save_path, f"audio_{idx}.wav") 55 | torchaudio.save(audio_path, audio, sample_rate) 56 | 57 | def get_binary_file_downloader_html(bin_file, file_label='File'): 58 | with open(bin_file, 'rb') as f: 59 | data = f.read() 60 | bin_str = base64.b64encode(data).decode() 61 | href = f'Download {file_label}' 62 | return href 63 | 64 | st.set_page_config( 65 | page_icon= "musical_note", 66 | page_title= "Music Gen" 67 | ) 68 | 69 | def main(): 70 | 71 | st.title("Text to Music Generator🎵") 72 | 73 | with st.expander("See explanation"): 74 | st.write("Music Generator app built using Meta's Audiocraft library. We are using Music Gen Small model.") 75 | 76 | text_area = st.text_area("Enter your description.......") 77 | time_slider = st.slider("Select time duration (In Seconds)", 0, 20, 10) 78 | 79 | if text_area and time_slider: 80 | st.json({ 81 | 'Your Description': text_area, 82 | 'Selected Time Duration (in Seconds)': time_slider 83 | }) 84 | 85 | st.subheader("Generated Music") 86 | music_tensors = generate_music_tensors(text_area, time_slider) 87 | print("Musci Tensors: ", music_tensors) 88 | save_music_file = save_audio(music_tensors) 89 | audio_filepath = 'audio_output/audio_0.wav' 90 | audio_file = open(audio_filepath, 'rb') 91 | audio_bytes = audio_file.read() 92 | st.audio(audio_bytes) 93 | st.markdown(get_binary_file_downloader_html(audio_filepath, 'Audio'), unsafe_allow_html=True) 94 | 95 | 96 | if __name__ == "__main__": 97 | main() 98 | 99 | 100 | 101 | -------------------------------------------------------------------------------- /audio_output/audio_0.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AIAnytime/Text-to-Music-Generation-App/2cec034f2dad26bcfe82f7c8116dd42017672835/audio_output/audio_0.wav -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | 2 | av 3 | einops 4 | flashy>=0.0.1 5 | hydra-core>=1.1 6 | hydra_colorlog 7 | julius 8 | num2words 9 | numpy 10 | sentencepiece 11 | spacy==3.5.2 12 | torch>=2.0.0 13 | torchaudio>=2.0.0 14 | huggingface_hub 15 | tqdm 16 | transformers>=4.31.0 # need Encodec there. 17 | xformers 18 | demucs 19 | librosa 20 | gradio 21 | torchmetrics 22 | encodec 23 | --------------------------------------------------------------------------------