├── Auto_trans_GUI.py
├── GUI.py
├── README.md
├── Sil-adder-GUI.py
├── cannedbread_genon2db_GUI.py
├── config.yaml
├── convert-phonemes-seg-GUI.py
├── convert_kana_GUI.py
├── hiragana.json
├── kiritan_script_GUI.py
├── lab2seg_GUI.py
├── phoneme_grabber_GUI.py
├── phonemes.json
├── requirements.txt
└── trans_convert_GUI.py


/Auto_trans_GUI.py:
--------------------------------------------------------------------------------
  1 | import tkinter as tk
  2 | from tkinter import ttk
  3 | import subprocess
  4 | import glob
  5 | import json
  6 | from tkinter import filedialog  # Import filedialog
  7 | from os import path
  8 | 
  9 | # Create a tkinter window
 10 | root = tk.Tk()
 11 | root.title("Auto-trans")
 12 | 
 13 | # Import the tcl file for the Forest theme
 14 | root.tk.call("source", "./Forest-ttk-theme-1.0/forest-dark.tcl")
 15 | 
 16 | # Set the theme with the theme_use method
 17 | style = ttk.Style(root)
 18 | style.theme_use("forest-dark")
 19 | 
 20 | # Create a BooleanVar with global scope
 21 | trans_check_var = tk.BooleanVar()
 22 | 
 23 | # Function to run the Auto-trans script
 24 | def run_auto_trans():
 25 |     # Your Auto-trans script code here
 26 |     jsonfile = open("hiragana.json", encoding='UTF-8', errors='ignore')
 27 |     pDict = json.load(jsonfile)
 28 |     jsonfile.close()
 29 |     
 30 |     wav_path = wav_entry.get()
 31 |     wav_path = wav_path + "\\"
 32 |     wav_files = glob.glob(f'{wav_path}*.wav')
 33 |     
 34 |     creating_ask = trans_check_var.get()
 35 |     auto_creating = False
 36 |     if creating_ask:
 37 |         auto_creating = True
 38 | 
 39 |     for filepath in wav_files:
 40 |         name = path.basename(filepath)
 41 |         name = path.splitext(name)[0]
 42 | 
 43 |         filepath = filepath.replace(".wav", ".trans")
 44 |         trans_file = open(filepath, "w+")
 45 |         if auto_creating:
 46 |             nameLen = len(name)
 47 |             phoneme = "Sil "
 48 |             findCheck = False
 49 |             for i in range(0, nameLen):
 50 |                 findCheck = False
 51 |                 if i + 1 < nameLen:
 52 |                     for obj in pDict:
 53 |                         if obj['kana'] == (name[i] + name[i + 1]):
 54 |                             phoneme += obj['phoneme'] + " "
 55 |                             findCheck = True
 56 |                             break
 57 |                     if not findCheck:
 58 |                         for obj in pDict:
 59 |                             if obj['kana'] == (name[i]):
 60 |                                 phoneme += obj['phoneme'] + " "
 61 |                                 break
 62 |                 else:
 63 |                     for obj in pDict:
 64 |                         if obj['kana'] == (name[i]):
 65 |                             phoneme += obj['phoneme'] + " "
 66 |                             break
 67 | 
 68 |             phoneme += "Sil"
 69 | 
 70 |             trans_file.write(phoneme)
 71 |             phonlist = phoneme.split()
 72 |             phonLen = len(phonlist)
 73 |             for i in range(0, phonLen):
 74 |                 if i < phonLen - 1:
 75 |                     trans_file.write("\n[" + phonlist[i] + " " + phonlist[i + 1] + "]")
 76 |                 else:
 77 |                     break
 78 | 
 79 |         trans_file.close()
 80 |     
 81 |     result_text.config(state=tk.NORMAL)
 82 |     result_text.delete("1.0", tk.END)
 83 |     result_text.insert(tk.END, "Process Completed!")
 84 |     result_text.config(state=tk.DISABLED)
 85 | 
 86 | def browse_wav_directory():
 87 |     wav_directory = filedialog.askdirectory()  # Open directory dialog
 88 |     wav_entry.delete(0, tk.END)  # Clear any previous input
 89 |     wav_entry.insert(0, wav_directory)  # Insert selected directory path
 90 | 
 91 | # Create a frame for the Auto-trans page
 92 | auto_trans_page = tk.Frame(root)
 93 | auto_trans_page.pack(padx=20, pady=20)
 94 | 
 95 | # Create a label and entry for the wav directory
 96 | wav_label = tk.Label(auto_trans_page, text="Enter wav directory:")
 97 | wav_label.pack()
 98 | wav_entry = tk.Entry(auto_trans_page)
 99 | wav_entry.pack()
100 | browse_button = ttk.Button(auto_trans_page, text="Browse", command=browse_wav_directory)
101 | browse_button.pack()
102 | 
103 | # Create a checkbox for transcription writing
104 | trans_check = ttk.Checkbutton(auto_trans_page, text="Write transcriptions automatically", variable=trans_check_var)
105 | trans_check.pack()
106 | 
107 | # Create a "Run" button
108 | run_button = ttk.Button(auto_trans_page, text="Run Auto-trans Script", command=run_auto_trans)
109 | run_button.pack()
110 | 
111 | # Create a text widget for the script output
112 | result_text = tk.Text(auto_trans_page, height=5, width=40, state=tk.DISABLED)
113 | result_text.pack()
114 | 
115 | # Start the tkinter main loop
116 | root.mainloop()
117 | 


--------------------------------------------------------------------------------
/GUI.py:
--------------------------------------------------------------------------------
  1 | import tkinter as tk
  2 | from tkinter import ttk
  3 | import subprocess
  4 | 
  5 | def run_script(script_path):
  6 |     try:
  7 |         process = subprocess.Popen(script_path, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True, universal_newlines=True)
  8 |         stdout, stderr = process.communicate()
  9 |         return stdout
 10 |     except Exception as e:
 11 |         return str(e)
 12 | 
 13 | # Create the main application window
 14 | root = tk.Tk()
 15 | root.title("Canned_Bread's VOCALOIDDBTOOL Swiss Army Knife")
 16 | root.geometry("800x600")  # Set the initial window size
 17 | 
 18 | # Make the app responsive
 19 | for i in range(3):
 20 |     root.columnconfigure(index=i, weight=1)
 21 | for i in range(3):
 22 |     root.rowconfigure(index=i, weight=1)
 23 | 
 24 | # Create a style
 25 | style = ttk.Style(root)
 26 | 
 27 | # Import the tcl file
 28 | root.tk.call("source", "./Forest-ttk-theme-1.0/forest-dark.tcl")
 29 | 
 30 | # Set the theme with the theme_use method
 31 | style.theme_use("forest-dark")
 32 | 
 33 | # Create a notebook for multiple script pages
 34 | notebook = ttk.Notebook(root)
 35 | 
 36 | # Define the "Trans Tools" page
 37 | trans_tools_page = ttk.Frame(notebook)
 38 | 
 39 | # Create a Frame for buttons on the "Trans Tools" page
 40 | trans_tools_button_frame = ttk.Frame(trans_tools_page)
 41 | trans_tools_button_frame.grid(row=0, column=1, padx=10, pady=(30, 10))
 42 | 
 43 | # Create a custom style for buttons
 44 | ttk.Style().configure('Custom.TButton', background='blue', foreground='white')
 45 | 
 46 | # Run button for "Auto_Trans"
 47 | def run_auto_trans():
 48 |     script_path = "Auto_trans_GUI.py"  # Replace with your script path
 49 |     output = run_script(script_path)
 50 |     trans_tools_output_text.config(state=tk.NORMAL)
 51 |     trans_tools_output_text.delete("1.0", tk.END)
 52 |     trans_tools_output_text.insert(tk.END, output)
 53 |     trans_tools_output_text.config(state=tk.DISABLED)
 54 | 
 55 | run_button_auto_trans = ttk.Button(trans_tools_button_frame, text="Run Auto_Trans", style='Custom.TButton', command=run_auto_trans)
 56 | run_button_auto_trans.pack(pady=10)
 57 | 
 58 |     
 59 | def run_trans_convert():
 60 |     script_path = "trans_convert_GUI.py"  
 61 |     output = run_script(script_path)
 62 |     trans_tools_output_text.config(state=tk.NORMAL)
 63 |     trans_tools_output_text.delete("1.0", tk.END)
 64 |     trans_tools_output_text.insert(tk.END, output)
 65 |     trans_tools_output_text.config(state=tk.DISABLED)
 66 | 
 67 | run_button_auto_trans = ttk.Button(trans_tools_button_frame, text="Run Trans Converter", style='Custom.TButton', command=run_trans_convert)
 68 | run_button_auto_trans.pack(pady=10)
 69 | 
 70 | # Create a Label widget with the desired text
 71 | trans_tools_description = ttk.Label(
 72 |     trans_tools_page,
 73 |     text="The first step in Vocaloid creation is the .trans files collection. Here you can run Auto_Trans to generate those for you (based off of WAV filename). \nTrans_converter is a tool that converts the Articulation .trans you get with auto_trans and makes them into Stationary .trans files (yes they're different).",
 74 |     wraplength=400  # Adjust this value as needed to fit the text within the desired width
 75 | )
 76 | trans_tools_description.grid(row=2, column=1, pady=(0, 10), columnspan=3)
 77 | 
 78 | # Output text widget for "Trans Tools" page
 79 | trans_tools_output_text = tk.Text(trans_tools_page, height=10, width=40, state=tk.DISABLED)
 80 | trans_tools_output_text.grid(row=1, column=1)
 81 | 
 82 | # Define the "oto.ini _> seg file tools" page
 83 | oto_ini_page = ttk.Frame(notebook)
 84 | 
 85 | # Create a Frame for buttons on the "oto.ini _> seg file tools" page
 86 | oto_ini_button_frame = ttk.Frame(oto_ini_page)
 87 | oto_ini_button_frame.grid(row=0, column=1, padx=10, pady=(30, 10))
 88 | 
 89 | # Run button for "Your Script 1"
 90 | def run_your_script_1():
 91 |     script_path = "cannedbread_genon2db_GUI.py" 
 92 |     output = run_script(script_path)
 93 |     oto_ini_output_text.config(state=tk.NORMAL)
 94 |     oto_ini_output_text.delete("1.0", tk.END)
 95 |     oto_ini_output_text.insert(tk.END, output)
 96 |     oto_ini_output_text.config(state=tk.DISABLED)
 97 | 
 98 | run_button_your_script_1 = ttk.Button(oto_ini_button_frame, text="Run genon2db", style='Custom.TButton', command=run_your_script_1)
 99 | run_button_your_script_1.pack(pady=10)
100 | 
101 | # Run button for "Your Script 2"
102 | def run_your_script_2():
103 |     script_path = "lab2seg_GUI.py"  
104 |     output = run_script(script_path)
105 |     oto_ini_output_text.config(state=tk.NORMAL)
106 |     oto_ini_output_text.delete("1.0", tk.END)
107 |     oto_ini_output_text.insert(tk.END, output)
108 |     oto_ini_output_text.config(state=tk.DISABLED)
109 | 
110 | run_button_your_script_2 = ttk.Button(oto_ini_button_frame, text="Run lab2seg", style='Custom.TButton', command=run_your_script_2)
111 | run_button_your_script_2.pack(pady=10)
112 | 
113 | # Output text widget for "oto.ini _> seg file tools" page
114 | oto_ini_output_text = tk.Text(oto_ini_page, height=10, width=40, state=tk.DISABLED)
115 | oto_ini_output_text.grid(row=1, column=1)
116 | 
117 | # Create a Label widget with the desired text
118 | oto_ini_description = ttk.Label(
119 |     oto_ini_page,
120 |     text="Genon2DB is a tool in which you can convert your oto.ini to .lab files for the next step. \nLab2Seg is where you take lab files and convert them into seg files for articulation .trans files (I need to make one for stationary because they're different too).",
121 |     wraplength=400  # Adjust this value as needed to fit the text within the desired width
122 | )
123 | oto_ini_description.grid(row=2, column=1, pady=(0, 10), columnspan=3)
124 | 
125 | 
126 | # Define the "Misc. Tools" page
127 | misc_tools_page = ttk.Frame(notebook)
128 | 
129 | # Create a Frame for buttons on the "Misc. Tools" page
130 | misc_tools_button_frame = ttk.Frame(misc_tools_page)
131 | misc_tools_button_frame.grid(row=0, column=1, padx=10, pady=(30, 10))
132 | 
133 | # Run button for "Phoneme Grabber"
134 | def run_phoneme_grabber():
135 |     script_path = "phoneme_grabber_GUI.py"  
136 |     output = run_script(script_path)
137 |     trans_tools_output_text.config(state=tk.NORMAL)
138 |     trans_tools_output_text.delete("1.0", tk.END)
139 |     trans_tools_output_text.insert(tk.END, output)
140 |     trans_tools_output_text.config(state=tk.DISABLED)
141 | 
142 | run_button_phoneme_grabber = ttk.Button(misc_tools_button_frame, text="Run Phoneme Grabber", style='Custom.TButton', command=run_phoneme_grabber)
143 | run_button_phoneme_grabber.pack(pady=10)
144 | 
145 | # Run button for "Your Script 3" (Miscellaneous script 1)
146 | def run_misc_script_1():
147 |     script_path = "convert_kana_GUI.py"  
148 |     output = run_script(script_path)
149 |     misc_tools_output_text.config(state=tk.NORMAL)
150 |     misc_tools_output_text.delete("1.0", tk.END)
151 |     misc_tools_output_text.insert(tk.END, output)
152 |     misc_tools_output_text.config(state=tk.DISABLED)
153 | 
154 | run_button_misc_script_1 = ttk.Button(misc_tools_button_frame, text="Run Convert Kana (lab)", style='Custom.TButton', command=run_misc_script_1)
155 | run_button_misc_script_1.pack(pady=10)
156 | 
157 | # Run button for "Your Script 4" (Miscellaneous script 2)
158 | def run_misc_script_2():
159 |     script_path = "kiritan_script_GUI.py" 
160 |     output = run_script(script_path)
161 |     misc_tools_output_text.config(state=tk.NORMAL)
162 |     misc_tools_output_text.delete("1.0", tk.END)
163 |     misc_tools_output_text.insert(tk.END, output)
164 |     misc_tools_output_text.config(state=tk.DISABLED)
165 | 
166 | run_button_misc_script_2 = ttk.Button(misc_tools_button_frame, text="Run Phoneme Transfer (wonky)", style='Custom.TButton', command=run_misc_script_2)
167 | run_button_misc_script_2.pack(pady=10)
168 | 
169 | # Run button for "Your Script 5" (Miscellaneous script 3)
170 | def run_misc_script_3():
171 |     script_path = "Sil-adder-GUI.py" 
172 |     output = run_script(script_path)
173 |     misc_tools_output_text.config(state=tk.NORMAL)
174 |     misc_tools_output_text.delete("1.0", tk.END)
175 |     misc_tools_output_text.insert(tk.END, output)
176 |     misc_tools_output_text.config(state=tk.DISABLED)
177 | 
178 | run_button_misc_script_3 = ttk.Button(misc_tools_button_frame, text="Run Sil adder", style='Custom.TButton', command=run_misc_script_3)
179 | run_button_misc_script_3.pack(pady=10)
180 | 
181 | # Run button for "Your Script 6" (Miscellaneous script 4)
182 | def run_misc_script_4():
183 |     script_path = "convert-phonemes-seg-GUI.py" 
184 |     output = run_script(script_path)
185 |     misc_tools_output_text.config(state=tk.NORMAL)
186 |     misc_tools_output_text.delete("1.0", tk.END)
187 |     misc_tools_output_text.insert(tk.END, output)
188 |     misc_tools_output_text.config(state=tk.DISABLED)
189 | 
190 | run_button_misc_script_4 = ttk.Button(misc_tools_button_frame, text="Run Phoneme converter (seg)", style='Custom.TButton', command=run_misc_script_4)
191 | run_button_misc_script_4.pack(pady=10)
192 | 
193 | # Output text widget for "Misc. Tools" page
194 | misc_tools_output_text = tk.Text(misc_tools_page, height=10, width=40, state=tk.DISABLED)
195 | misc_tools_output_text.grid(row=1, column=1)
196 | 
197 | # Create a Label widget with the desired text
198 | misc_tools_description = ttk.Label(
199 |     misc_tools_page,
200 |     text="Phoneme Grabber is a tool that takes all of your phonemes from an oto.ini file and it generates a text file with all of the phonemes in it. It's useful for editing hiragana.json or phonemes.json.\nConvert Kana (lab) is a tool that converts kana in your labs to phonemes for the seg creation.\nPhoneme transfer is an experimental script that transfers phonemes from one seg file to another (for when you have a voicebank with many pitches and you want the timings to be different but the phonemes to be the same in a set of seg files\nSil adder is a tool to add Sil phonemes to the beginning of your .seg files.\nPhoneme comverter (seg) converts phonemes in your seg files.",    wraplength=400  # Adjust this value as needed to fit the text within the desired width
201 | )
202 | misc_tools_description.grid(row=2, column=1, pady=(0, 10), columnspan=3)
203 | 
204 | 
205 | # Add the pages to the notebook
206 | notebook.add(trans_tools_page, text="Trans Tools")
207 | notebook.add(oto_ini_page, text="oto.ini -> seg file tools")
208 | notebook.add(misc_tools_page, text="Misc. Tools")
209 | 
210 | # Pack the notebook
211 | notebook.grid(row=0, column=1, padx=10, pady=(30, 10))
212 | 
213 | # Center the window and set minsize
214 | root.update()
215 | root.minsize(root.winfo_width(), root.winfo_height())
216 | x_cordinate = int((root.winfo_screenwidth()/2) - (root.winfo_width()/2))
217 | y_cordinate = int((root.winfo_screenheight()/2) - (root.winfo_height()/2))
218 | root.geometry("+{}+{}".format(x_cordinate, y_cordinate))
219 | 
220 | # Start the main loop
221 | root.mainloop()
222 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Canned-Bread's VOCALOIDDBTOOL Swiss Army Knife
 2 | 
 3 | # UPDATE ON THE TOOL!
 4 | 
 5 | Since other tools are better and more useful, I decided to archive this tool since I'm not working in the vocal synth space anymore... Sorry...
 6 | 
 7 | Canned-Bread's VOCALOIDDBTOOL Swiss Army Knife, which allows you to do some pretty cool things for HOMEBREW VOCALOID development!
 8 | 
 9 | Uses a modded Genon2NNSVS from https://github.com/oatsu-gh/genon2nnsvs
10 | 
11 | Also uses a modded Auto-Trans from https://github.com/EgorV4/auto-trans
12 | 
13 | Uses https://github.com/rdbende/Forest-ttk-theme
14 | 
15 | # HOW TO RUN
16 | 
17 | Have python 3.10 installed https://www.python.org/downloads/release/python-3100/
18 | 
19 | Have requirements pydub==0.25.1 and utaupy==1.18.3 installed 
20 | 
21 | 
22 | `pip install pydub==0.25.1 utaupy==1.18.3`
23 | 
24 | Run GUI.py and select what you'd like to do
25 | 
26 | 
27 | Please let me know if anything needs changes!
28 | 
29 | DOWNLOAD FROM RELEASES IT HAS ALL FILES NEEDED!
30 | 
31 | # HOW TO UPDATE
32 | 
33 | Download the code in a zip and replace the python files
34 | 
35 | Here's a screenshot:
36 | ![image](https://github.com/bread-in-a-can/Canned-Bread-s-VOCALOIDDBTOOL-Swiss-Army-Knife/assets/124006393/7b2edccf-2bfe-47c6-b1e7-723d076b7661)
37 | 
38 | 
39 | 
40 | 
41 | Yamaha plz don't kill me
42 | 


--------------------------------------------------------------------------------
/Sil-adder-GUI.py:
--------------------------------------------------------------------------------
  1 | import os
  2 | import argparse
  3 | import tkinter as tk
  4 | from tkinter import ttk
  5 | from tkinter import filedialog
  6 | 
  7 | 
  8 | def add_sil_phonemes(input_directory, output_directory, add_sil_at_beginning, add_sil_at_end):
  9 |     # Create the output directory if it doesn't exist
 10 |     if not os.path.exists(output_directory):
 11 |         os.makedirs(output_directory)
 12 | 
 13 |     # Process each seg file in the input directory
 14 |     for seg_file_name in os.listdir(input_directory):
 15 |         if seg_file_name.endswith(".seg"):
 16 |             input_seg_file = os.path.join(input_directory, seg_file_name)
 17 |             output_seg_file = os.path.join(output_directory, seg_file_name)
 18 | 
 19 |             # Read the original .seg file
 20 |             with open(input_seg_file, 'r') as infile:
 21 |                 lines = infile.readlines()
 22 | 
 23 |             # Find the line index where the "=====" line appears
 24 |             separator_line_index = lines.index("=================================================\n")
 25 | 
 26 |             # Extract the timing information from the first non-empty phoneme line
 27 |             first_non_empty_phoneme_start = None
 28 |             first_non_empty_phoneme_end = None
 29 | 
 30 |             for line in lines[separator_line_index + 1:]:
 31 |                 phoneme_values = line.strip().split('\t')
 32 |                 if len(phoneme_values) >= 3:
 33 |                     first_non_empty_phoneme_start = phoneme_values[1]
 34 |                     first_non_empty_phoneme_end = phoneme_values[2]
 35 |                     break
 36 | 
 37 |             if add_sil_at_beginning:
 38 |                 # Insert "Sil" at the top with the calculated end time
 39 |                 new_sil_line = f"Sil\t\t0.000000\t\t{first_non_empty_phoneme_end}\n"
 40 |                 lines.insert(separator_line_index + 1, new_sil_line)
 41 | 
 42 |             if add_sil_at_end:
 43 |                 # Calculate the number of phonemes
 44 |                 num_phonemes = len(lines) - separator_line_index
 45 | 
 46 |             # Update the "nPhonemes" line with the calculated count
 47 |             for i, line in enumerate(lines):
 48 |                 if line.startswith("nPhonemes"):
 49 |                     current_value = int(line.split()[-1])
 50 |                     new_value = current_value + 1
 51 |                     lines[i] = f"nPhonemes {new_value}\n"
 52 |                     break
 53 | 
 54 |                 # Find the last non-empty phoneme's end time
 55 |                 last_non_empty_phoneme_end = first_non_empty_phoneme_end
 56 |                 for line in reversed(lines[separator_line_index + 1:]):
 57 |                     phoneme_values = line.strip().split('\t')
 58 |                     if len(phoneme_values) >= 3:
 59 |                         last_non_empty_phoneme_end = phoneme_values[2]
 60 |                         break
 61 | 
 62 |                 # Find the largest end time in the .seg file
 63 |                 largest_end_time = max(float(phoneme_values[2]) for line in lines[separator_line_index + 1:])
 64 | 
 65 |                 # Format the largest_end_time to include all decimals and zero if it's a whole number
 66 |                 if largest_end_time.is_integer():
 67 |                     largest_end_time = f"{largest_end_time:.6f}"
 68 |                 else:
 69 |                     largest_end_time = str(largest_end_time)
 70 | 
 71 |                     # Set the "Sil" at the end with the largest end time
 72 |                     lines[-1] = f"Sil\t\t{last_non_empty_phoneme_end}\t\t{last_non_empty_phoneme_end}\n"
 73 | 
 74 | 
 75 |             # Open the output .seg file for writing
 76 |             with open(output_seg_file, 'w') as outfile:
 77 |                 # Write the entire modified list back to the file
 78 |                 outfile.writelines(lines)
 79 | 
 80 |             print("Sil phonemes added to", seg_file_name)
 81 | 
 82 |     print("All modifications complete.")
 83 | 
 84 | def browse_input_directory():
 85 |     input_directory = filedialog.askdirectory()
 86 |     input_directory_entry.delete(0, tk.END)
 87 |     input_directory_entry.insert(0, input_directory)
 88 | 
 89 | def browse_output_directory():
 90 |     output_directory = filedialog.askdirectory()
 91 |     output_directory_entry.delete(0, tk.END)
 92 |     output_directory_entry.insert(0, output_directory)
 93 | 
 94 | def execute_script():
 95 |     input_directory = input_directory_entry.get()
 96 |     output_directory = output_directory_entry.get()
 97 |     add_sil_at_beginning = add_sil_at_beginning_var.get()
 98 |     add_sil_at_end = add_sil_at_end_var.get()
 99 |     add_sil_phonemes(input_directory, output_directory, add_sil_at_beginning, add_sil_at_end)
100 |     result_label.config(text="Modifications complete.")
101 | 
102 | # Create the main window
103 | root = tk.Tk()
104 | root.title("Add 'Sil' Phonemes")
105 | 
106 | # Import the tcl file
107 | root.tk.call("source", "./Forest-ttk-theme-1.0/forest-dark.tcl")
108 | 
109 | # Set the theme with the theme_use method
110 | style = ttk.Style()
111 | style.theme_use("forest-dark")
112 | 
113 | # Create and configure widgets
114 | input_directory_label = ttk.Label(root, text="Input Directory:")
115 | input_directory_entry = ttk.Entry(root)
116 | browse_input_button = ttk.Button(root, text="Browse", command=browse_input_directory)
117 | 
118 | output_directory_label = ttk.Label(root, text="Output Directory:")
119 | output_directory_entry = ttk.Entry(root)
120 | browse_output_button = ttk.Button(root, text="Browse", command=browse_output_directory)
121 | 
122 | add_sil_at_beginning_var = tk.BooleanVar()
123 | add_sil_at_beginning_checkbox = ttk.Checkbutton(root, text="Add 'Sil' at the beginning", variable=add_sil_at_beginning_var)
124 | 
125 | add_sil_at_end_var = tk.BooleanVar()
126 | add_sil_at_end_checkbox = ttk.Checkbutton(root, text="Add 'Sil' at the end (EXPERIMENTAL/BROKEN)", variable=add_sil_at_end_var)
127 | 
128 | execute_button = ttk.Button(root, text="Execute", command=execute_script)
129 | result_label = ttk.Label(root, text="")
130 | 
131 | # Layout widgets
132 | input_directory_label.grid(row=0, column=0, padx=10, pady=5)
133 | input_directory_entry.grid(row=0, column=1, padx=10, pady=5)
134 | browse_input_button.grid(row=0, column=2, padx=10, pady=5)
135 | 
136 | output_directory_label.grid(row=1, column=0, padx=10, pady=5)
137 | output_directory_entry.grid(row=1, column=1, padx=10, pady=5)
138 | browse_output_button.grid(row=1, column=2, padx=10, pady=5)
139 | 
140 | add_sil_at_beginning_checkbox.grid(row=2, column=1, padx=10, pady=5)
141 | add_sil_at_end_checkbox.grid(row=3, column=1, padx=10, pady=5)
142 | 
143 | execute_button.grid(row=4, column=1, padx=10, pady=10)
144 | result_label.grid(row=5, column=1, padx=10, pady=5)
145 | 
146 | root.mainloop()
147 | 


--------------------------------------------------------------------------------
/cannedbread_genon2db_GUI.py:
--------------------------------------------------------------------------------
  1 | import tkinter as tk
  2 | from tkinter import ttk, filedialog
  3 | import utaupy as up
  4 | from os.path import abspath, basename, dirname, isdir, join
  5 | from shutil import copy
  6 | from pydub import AudioSegment
  7 | from operator import attrgetter
  8 | from glob import glob
  9 | from os import makedirs
 10 | 
 11 | NOTENAME_TO_NOTENUM_DICT = {
 12 |     "C3": 48, "D3": 50, "E3": 52, "F3": 53, "G3": 55, "A3": 57, "B3": 59,
 13 |     "C4": 60, "D4": 62, "E4": 64, "F4": 65, "G4": 67, "A4": 69, "B4": 71,
 14 |     "C5": 72
 15 | }
 16 | 
 17 | class USTGeneratorApp:
 18 |     def __init__(self, root):
 19 |         self.root = root
 20 |         self.root.title("Genon2DB")
 21 |         self.style = ttk.Style(self.root)
 22 | 
 23 |         # Import the tcl file for the Forest theme
 24 |         self.root.tk.call("source", "./Forest-ttk-theme-1.0/forest-dark.tcl")
 25 | 
 26 |         # Set the theme with the theme_use method
 27 |         self.style.theme_use("forest-dark")
 28 | 
 29 |         self.frame = ttk.Frame(self.root, padding=(10, 10))
 30 |         self.frame.grid(row=0, column=0)
 31 | 
 32 |         self.create_widgets()
 33 |         self.create_output_console()
 34 | 
 35 |     def create_output_console(self):
 36 |         self.output_console = tk.Text(self.frame, wrap=tk.WORD, width=60, height=20)
 37 |         self.output_console.grid(row=8, column=0, columnspan=3, pady=10)
 38 |         self.scrollbar = ttk.Scrollbar(self.frame, command=self.output_console.yview)
 39 |         self.output_console.config(yscrollcommand=self.scrollbar.set)
 40 |         self.scrollbar.grid(row=8, column=3, sticky='nsew')
 41 | 
 42 |     def update_output_console(self, message):
 43 |         self.output_console.insert(tk.INSERT, message)
 44 |         self.output_console.see(tk.INSERT)
 45 | 
 46 |     def create_widgets(self):
 47 |         self.label1 = ttk.Label(self.frame, text="Original Configuration File:")
 48 |         self.label1.grid(row=0, column=0, sticky="w")
 49 | 
 50 |         self.otoini_path = tk.StringVar()
 51 |         self.otoini_entry = ttk.Entry(self.frame, textvariable=self.otoini_path)
 52 |         self.otoini_entry.grid(row=0, column=1, padx=10)
 53 | 
 54 |         self.browse_otoini_button = ttk.Button(self.frame, text="Browse", command=self.browse_otoini)
 55 |         self.browse_otoini_button.grid(row=0, column=2)
 56 | 
 57 |         self.label4 = ttk.Label(self.frame, text="Table File:")
 58 |         self.label4.grid(row=1, column=0, sticky="w")
 59 | 
 60 |         self.table_path = tk.StringVar()
 61 |         self.table_entry = ttk.Entry(self.frame, textvariable=self.table_path)
 62 |         self.table_entry.grid(row=1, column=1, padx=10)
 63 | 
 64 |         self.browse_table_button = ttk.Button(self.frame, text="Browse", command=self.browse_table)
 65 |         self.browse_table_button.grid(row=1, column=2)
 66 | 
 67 |         self.label6 = ttk.Label(self.frame, text="Output Directory:")
 68 |         self.label6.grid(row=2, column=0, sticky="w")
 69 | 
 70 |         self.output_dir_path = tk.StringVar()
 71 |         self.output_dir_entry = ttk.Entry(self.frame, textvariable=self.output_dir_path)
 72 |         self.output_dir_entry.grid(row=2, column=1, padx=10)
 73 | 
 74 |         self.browse_output_dir_button = ttk.Button(self.frame, text="Browse", command=self.browse_output_dir)
 75 |         self.browse_output_dir_button.grid(row=2, column=2)
 76 | 
 77 |         self.label2 = ttk.Label(self.frame, text="Tempo:")
 78 |         self.label2.grid(row=3, column=0, sticky="w")
 79 | 
 80 |         self.tempo = tk.DoubleVar()
 81 |         self.tempo_entry = ttk.Entry(self.frame, textvariable=self.tempo)
 82 |         self.tempo_entry.grid(row=3, column=1, padx=10)
 83 | 
 84 |         self.label3 = ttk.Label(self.frame, text="Initial Pause Length in beats (put auto for auto estimation):")
 85 |         self.label3.grid(row=4, column=0, sticky="w")
 86 | 
 87 |         self.pause_length = tk.StringVar()
 88 |         self.pause_length_entry = ttk.Entry(self.frame, textvariable=self.pause_length)
 89 |         self.pause_length_entry.grid(row=4, column=1, padx=10)
 90 | 
 91 |         self.label5 = ttk.Label(self.frame, text="Note:")
 92 |         self.label5.grid(row=5, column=0, sticky="w")
 93 | 
 94 |         self.note = tk.StringVar()
 95 |         self.note_entry = ttk.Entry(self.frame, textvariable=self.note)
 96 |         self.note_entry.grid(row=5, column=1, padx=10)
 97 | 
 98 |         self.uta_vcv = tk.BooleanVar()
 99 |         self.uta_vcv_checkbox = ttk.Checkbutton(self.frame, text="Song Continuous Phoneme Recording (UTA VCV Mode)",
100 |                                                variable=self.uta_vcv)
101 |         self.uta_vcv_checkbox.grid(row=6, column=1)
102 | 
103 |         self.generate_button = ttk.Button(self.frame, text="Generate DB", command=self.generate_ust)
104 |         self.generate_button.grid(row=7, column=0, columnspan=3)
105 | 
106 |     def browse_otoini(self):
107 |         otoini_path = filedialog.askopenfilename(filetypes=[("oto.ini files", "*.ini")])
108 |         self.otoini_path.set(otoini_path)
109 | 
110 |     def browse_table(self):
111 |         table_path = filedialog.askopenfilename(filetypes=[("Table files", "*.table")])
112 |         self.table_path.set(table_path)
113 | 
114 |     def browse_output_dir(self):
115 |         output_dir = filedialog.askdirectory()
116 |         self.output_dir_path.set(output_dir)
117 | 
118 |     def force_otoinifile_cutoff_negative(self, path_otoini_in, path_otoini_out):
119 |         otoini = up.otoini.load(path_otoini_in)
120 |         voice_dir = dirname(path_otoini_in)
121 |         if any([oto.cutoff > 0 for oto in otoini]):
122 |             for oto in otoini:
123 |                 path_wav = join(voice_dir, oto.filename)
124 |                 sound = AudioSegment.from_file(path_wav, 'wav')
125 |                 duration_ms = 1000 * sound.duration_seconds
126 |                 absolute_cutoff_position = duration_ms - oto.cutoff
127 |                 oto.cutoff = -(absolute_cutoff_position - oto.offset)
128 |             otoini.write(path_otoini_out)
129 | 
130 |     def prepare_otoini(self, otoini):
131 |         otoini.data = [
132 |             oto for oto in otoini if all(
133 |                 [' ' in oto.alias, '息' not in oto.alias, 'を' not in oto.alias]
134 |             )
135 |         ]
136 |         for oto in otoini:
137 |             oto.alias = oto.alias.split()[-1].replace('-', 'R')
138 |         otoini.data = sorted(otoini.data, key=attrgetter('filename', 'offset'))
139 | 
140 |     def split_otoini(self, otoini):
141 |         l_2d = []
142 |         filename = ''
143 |         for oto in otoini:
144 |             if filename != oto.filename:
145 |                 filename = oto.filename
146 |                 temp_otoini = up.otoini.OtoIni()
147 |                 l_2d.append(temp_otoini)
148 |             temp_otoini.append(oto)
149 |         return l_2d
150 | 
151 |     def generate_ustobj(self, otoini, notenum, tempo, pause_length_by_beat):
152 |         ust = up.ust.Ust()
153 |         ust.version = 1.20
154 |         if not otoini:
155 |             return ust
156 | 
157 |         note = up.ust.Note()
158 |         note.lyric = 'R'
159 |         note.tempo = tempo
160 |         note.notenum = notenum
161 |         duration_ms = (otoini[0].offset + otoini[0].preutterance)
162 |         if pause_length_by_beat == 'auto':
163 |             note.length = 60 * round(duration_ms * tempo / 7500)
164 |         else:
165 |             try:
166 |                 pause_length_by_beat = int(pause_length_by_beat)
167 |                 note.length = int(pause_length_by_beat * 480)
168 |             except ValueError:
169 |                 print("Invalid pause length. Please enter a valid number or 'auto'.")
170 |         ust.notes.append(note)
171 | 
172 |         for oto in otoini:
173 |             note = up.ust.Note()
174 |             note.lyric = oto.alias
175 |             note.tempo = tempo
176 |             note.notenum = notenum
177 |             note.length = 480
178 |             ust.notes.append(note)
179 | 
180 |         if len(otoini) >= 2:
181 |             duration_ms = (
182 |                 (otoini[-1].offset + otoini[-1].preutterance) -
183 |                 (otoini[-2].offset + otoini[-2].preutterance)
184 |             )
185 |             ust.notes[-2].length = 60 * round(duration_ms * tempo / 7500)
186 |             duration_ms = (- otoini[-1].cutoff) - otoini[-1].preutterance
187 |             ust.notes[-1].length = 60 * round(duration_ms * tempo / 7500)
188 | 
189 |         return ust
190 | 
191 |     def configure_notenum_for_uta_vcv(self, ust):
192 |         for i, note in enumerate(ust.notes[1:-1], 1):
193 |             if i % 2 == 0:
194 |                 note.notenum += 1
195 |             else:
196 |                 note.notenum -= 1
197 |         ust.notes[0].notenum = ust.notes[1].notenum
198 |         ust.notes[-1].notenum = ust.notes[-2].notenum
199 | 
200 |     def generate_labelobj(self, otoini, d_table):
201 |         for oto in otoini:
202 |             oto.alias = ' '.join(d_table.get(oto.alias, [oto.alias]))
203 |         label = up.convert.otoini2label(otoini, mode='romaji_cv')
204 |         for phoneme in label:
205 |             if phoneme.symbol == 'sil':
206 |                 phoneme.symbol = 'pau'
207 |         return label
208 | 
209 |     def generate_labfile(self, path_otoini, path_table, out_dir, tempo, notename, uta_vcv_mode, pause_length):
210 |         self.force_otoinifile_cutoff_negative(path_otoini, path_otoini)
211 |         otoini = up.otoini.load(path_otoini)
212 |         self.prepare_otoini(otoini)
213 |         otoini_2d = self.split_otoini(otoini)
214 |         makedirs(join(out_dir, 'lab'), exist_ok=True)
215 |         makedirs(join(out_dir, 'ust'), exist_ok=True)
216 |         makedirs(join(out_dir, 'wav'), exist_ok=True)
217 | 
218 |         # Load the .table file for note mapping
219 |         table = self.load_table_file(path_table)
220 | 
221 |         for otoini in otoini_2d:
222 |             name = otoini[0].filename.replace('.wav', '')
223 |             ust = self.generate_ustobj(otoini, NOTENAME_TO_NOTENUM_DICT.get(notename, 60), tempo, pause_length)
224 | 
225 |             if uta_vcv_mode:
226 |                 self.configure_notenum_for_uta_vcv(ust)
227 | 
228 |             ust.write(join(out_dir, 'ust', f'{name}.ust'))
229 |             mono_label = self.generate_labelobj(otoini, table)
230 |             mono_label.write(join(out_dir, 'lab', f'{name}.lab'))
231 |             copy(join(dirname(path_otoini), f'{name}.wav'), join(out_dir, 'wav', f'{name}.wav'))
232 | 
233 |         print('UST and label files generated successfully.')
234 | 
235 |     def load_table_file(self, path_table):
236 |         table = {}
237 |         with open(path_table, 'r', encoding='utf-8') as file:
238 |             for line in file:
239 |                 parts = line.strip().split('\t')
240 |                 if len(parts) == 2:
241 |                     key, value = parts
242 |                     table[key] = value
243 |         return table
244 | 
245 |     def mono2full_and_round(self, mono_align_dir, full_score_dir, prefix):
246 |         mono_label_files = glob(f'{mono_align_dir}/{prefix}*.lab')
247 |         for path_mono in mono_label_files:
248 |             path_full = join(full_score_dir, basename(path_mono))
249 |             mono_label = up.label.load(path_mono)
250 |             full_label = up.label.load(path_full)
251 |             if len(mono_label) != len(full_label):
252 |                 print(f"Error: Mismatch in the number of phonemes in {basename(path_mono)}")
253 |                 continue
254 |             for mono_phoneme, full_phoneme in zip(mono_label, full_label):
255 |                 mono_phoneme.symbol = full_phoneme.symbol
256 |             mono_label.round(50000)
257 |             mono_label.data = [phoneme for phoneme in mono_label.data if phoneme.symbol != 'sil' and phoneme.symbol.strip()]
258 |             mono_label.write(path_mono)
259 | 
260 |         print('Mono-label files converted to full-label files and rounded.')
261 | 
262 |     def guess_notename_from_prefix(self, prefix, d_notename2notenum):
263 |         notenames = d_notename2notenum.keys()
264 |         for notename in notenames:
265 |             if prefix in notename:
266 |                 return notename
267 |         return None
268 | 
269 |     def generate_ust(self):
270 |         out_dir = self.output_dir_path.get()
271 |         path_otoini = self.otoini_path.get()
272 |         path_table = self.table_path.get()
273 |         tempo = self.tempo.get()
274 |         pause_length = self.pause_length.get()
275 |         prefix = basename(dirname(path_otoini))
276 |         notename = self.note.get()
277 |         uta_vcv_mode = self.uta_vcv.get()
278 | 
279 |         self.update_output_console('Converting oto.ini to label files and UST files and copying WAV files.\n')
280 |         self.generate_labfile(path_otoini, path_table, out_dir, tempo, notename, uta_vcv_mode, pause_length)
281 | 
282 |         self.update_output_console('Converting mono-label files to full-label files and rounding them.\n')
283 |         self.mono2full_and_round(join(out_dir, 'lab'), out_dir, prefix)
284 | 
285 |         self.update_output_console(f'All files were successfully saved to {abspath(out_dir)}\n')
286 | 
287 | if __name__ == '__main__':
288 |     root = tk.Tk()
289 |     app = USTGeneratorApp(root)
290 |     root.mainloop()
291 | 


--------------------------------------------------------------------------------
/config.yaml:
--------------------------------------------------------------------------------
 1 | ### General settings.
 2 | ## The name of singer
 3 | spk: raina_cute
 4 | 
 5 | ## exp tag(for managing experiments)
 6 | tag: jp_qst_crazy_mono_007_enunu_173D
 7 | 
 8 | ## Output directory
 9 | # 学習に使うデータを置く場所。genon_db_dir からここにファイルをコピーしてから学習する。
10 | # All the generated labels, intermediate files, and segmented wav files
11 | # will be saved in the following directory
12 | out_dir: ./data
13 | 
14 | ## Songs to be excluded from trainig.
15 | # NOTE: ここ未実装
16 | exclude_songs: []
17 | 
18 | ## table file for translating lyrics to phonemes.
19 | # NOTE: ラベル作るときに手動指定するので必要ない気がする。
20 | # TODO: 母音と母音の区別をつけるためのconfファイルも使うようにする。
21 | sinsy_dic: ./dic
22 | table_path: ./dic/intunist_jp_compatibility.table
23 | 
24 | ## HTS-style question used for extracting musical/linguistic context from musicxml files
25 | question_path: ./hed/jp_qst_crazy_mono_007_enunu_173D.hed
26 | 
27 | # Audio sampling rate
28 | # CAUTION: Changing sample_rate may affect the dimension number of acoustic features.
29 | # DO NOT CHANGE this unless you know the relationship between the dim of bap and sample_rate.
30 | sample_rate: 44100
31 | 
32 | ###########################################################
33 | #                FEATURE EXTRACTION SETTING               #
34 | ###########################################################
35 | 
36 | timelag_features: defaults
37 | duration_features: defaults
38 | acoustic_features: static_deltadelta
39 | 
40 | ###########################################################
41 | #                TRAINING SETTING                         #
42 | ###########################################################
43 | 
44 | # Models
45 | # To customize, put your config or change ones in
46 | # conf/train/{timelag,duration,acoustic}/ and
47 | # specify the config name below
48 | # NOTE: *_model: model definition, *_train: general train configs,
49 | # *_data: data configs (e.g., batch size)
50 | 
51 | timelag_model: timelag_ffn
52 | timelag_train: myconfig
53 | timelag_data: myconfig
54 | 
55 | duration_model: duration_lstm
56 | duration_train: myconfig
57 | duration_data: myconfig
58 | 
59 | acoustic_model: acoustic_conv
60 | acoustic_train: myconfig
61 | acoustic_data: myconfig
62 | 
63 | # Pretrained model dir (leave empty to disable)
64 | pretrained_expdir:
65 | 
66 | ###########################################################
67 | #                SYNTHESIS SETTING                        #
68 | ###########################################################
69 | timelag_synthesis: defaults
70 | duration_synthesis: defaults
71 | acoustic_synthesis: defaults
72 | 
73 | # latest.pth or best.pth
74 | timelag_eval_checkpoint: best_loss.pth
75 | duration_eval_checkpoint: best_loss.pth
76 | acoustic_eval_checkpoint: best_loss.pth
77 | 


--------------------------------------------------------------------------------
/convert-phonemes-seg-GUI.py:
--------------------------------------------------------------------------------
  1 | import os
  2 | import json
  3 | import tkinter as tk
  4 | from tkinter import ttk
  5 | from tkinter import filedialog
  6 | from tkinter import messagebox
  7 | 
  8 | # Load the phoneme JSON data
  9 | script_directory = os.path.dirname(os.path.abspath(__file__))
 10 | phonemes_json_path = os.path.join(script_directory, 'phonemes.json')
 11 | 
 12 | with open(phonemes_json_path, 'r') as file:
 13 |     phonemes_data = json.load(file)
 14 | 
 15 | # Create a dictionary for easy lookup
 16 | phonemes_dict = {entry['kana']: entry['phoneme'] for entry in phonemes_data}
 17 | 
 18 | # Function to convert kana sequence to phonemes
 19 | def convert_kana_sequence_to_phonemes(kana_sequence):
 20 |     words = kana_sequence.split()
 21 |     phonemes = []
 22 |     for word in words:
 23 |         phoneme = phonemes_dict.get(word, word)
 24 |         phonemes.append(phoneme)
 25 |     return ' '.join(phonemes)
 26 | 
 27 | # Function to process a single .seg file
 28 | def process_seg_file(input_path):
 29 |     with open(input_path, 'r', encoding='utf-8') as seg_file:
 30 |         seg_lines = seg_file.read().split('\n')
 31 | 
 32 |     converted_lines = []
 33 |     convert_lines = False
 34 |     header_lines = []
 35 | 
 36 |     for line in seg_lines:
 37 |         if line.startswith('='):
 38 |             convert_lines = True
 39 |             header_lines.append(line)
 40 |         elif convert_lines:
 41 |             parts = line.split()
 42 |             if len(parts) == 3:
 43 |                 kana_sequence, start_time, end_time = parts
 44 |                 phoneme_sequence = convert_kana_sequence_to_phonemes(kana_sequence)
 45 |                 converted_lines.append(f"{phoneme_sequence}\t\t{start_time}\t\t{end_time}")
 46 |             else:
 47 |                 converted_lines.append(line)
 48 | 
 49 |     n_phonemes = len(converted_lines)  # Subtract 1 to exclude the "=====" line
 50 |     header_lines.insert(0, f'nPhonemes {n_phonemes}')
 51 |     header_lines.insert(1, 'articulationsAreStationaries 0')
 52 |     header_lines.insert(2, 'phoneme   BeginTime   EndTime')
 53 | 
 54 |     converted_content = '\n'.join(header_lines + converted_lines)
 55 | 
 56 |     with open(input_path, 'w', encoding='utf-8') as seg_file:
 57 |         seg_file.write(converted_content)
 58 | 
 59 | def browse_directory():
 60 |     directory = filedialog.askdirectory()
 61 |     if directory:
 62 |         directory_entry.delete(0, tk.END)
 63 |         directory_entry.insert(0, directory)
 64 | 
 65 | def convert_files():
 66 |     directory = directory_entry.get()
 67 | 
 68 |     if not directory:
 69 |         messagebox.showerror("Error", "Please select a directory.")
 70 |         return
 71 | 
 72 |     for filename in os.listdir(directory):
 73 |         if filename.endswith(".seg"):
 74 |             input_path = os.path.join(directory, filename)
 75 |             process_seg_file(input_path)
 76 | 
 77 |     messagebox.showinfo("Success", "Conversion complete.")
 78 | 
 79 | # Create the main application window
 80 | root = tk.Tk()
 81 | root.title("SEG File Conversion")
 82 | 
 83 | # Create a style
 84 | style = ttk.Style(root)
 85 | 
 86 | # Import the tcl file
 87 | root.tk.call("source", "./Forest-ttk-theme-1.0/forest-dark.tcl")
 88 | 
 89 | # Set the theme with the theme_use method
 90 | style.theme_use("forest-dark")
 91 | 
 92 | # Create a frame for the input fields
 93 | input_frame = ttk.Frame(root, padding=10)
 94 | input_frame.grid(row=0, column=0, padx=10, pady=10, sticky='w')
 95 | 
 96 | # Directory selection
 97 | directory_label = ttk.Label(input_frame, text='Select Directory:')
 98 | directory_label.grid(row=0, column=0, sticky='w')
 99 | 
100 | directory_entry = ttk.Entry(input_frame, width=40)
101 | directory_entry.grid(row=0, column=1, padx=(5, 0), sticky='w')
102 | 
103 | directory_button = ttk.Button(input_frame, text='Browse', command=browse_directory)
104 | directory_button.grid(row=0, column=2, padx=(5, 0), sticky='w')
105 | 
106 | # Convert button
107 | convert_button = ttk.Button(root, text='Convert SEG Files', command=convert_files)
108 | convert_button.grid(row=1, column=0, padx=10, pady=10)
109 | 
110 | # Start the GUI application
111 | root.mainloop()
112 | 


--------------------------------------------------------------------------------
/convert_kana_GUI.py:
--------------------------------------------------------------------------------
  1 | import os
  2 | import json
  3 | import re
  4 | import argparse
  5 | import tkinter as tk
  6 | from tkinter import ttk
  7 | from tkinter import filedialog
  8 | from tkinter import messagebox
  9 | 
 10 | # Load the hiragana JSON data from the same directory as the script
 11 | script_directory = os.path.dirname(os.path.abspath(__file__))
 12 | hiragana_json_path = os.path.join(script_directory, 'hiragana.json')
 13 | 
 14 | with open(hiragana_json_path, 'r', encoding='utf-8') as file:
 15 |     hiragana_data = json.load(file)
 16 | 
 17 | # Create a dictionary for easy lookup
 18 | hiragana_dict = {entry['kana']: entry['phoneme'] for entry in hiragana_data}
 19 | 
 20 | # Create a set to store unknown kana characters
 21 | unknown_kana = set()
 22 | 
 23 | # Function to convert kana sequence to phonemes
 24 | def convert_kana_sequence_to_phonemes(kana_sequence):
 25 |     words = kana_sequence.split()
 26 |     phonemes = []
 27 |     for word in words:
 28 |         phoneme = hiragana_dict.get(word, word)
 29 |         if phoneme == word:
 30 |             unknown_kana.add(word)  # Add unknown kana characters to the set
 31 |         phonemes.append(phoneme)
 32 |     return ' '.join(phonemes)
 33 | 
 34 | # Function to process a single .lab file
 35 | def process_lab_file(input_path):
 36 |     with open(input_path, 'r', encoding='utf-8') as lab_file:
 37 |         lab_content = lab_file.read()
 38 | 
 39 |     lines = lab_content.split('\n')
 40 |     converted_lines = []
 41 | 
 42 |     for line in lines:
 43 |         if not line:
 44 |             continue
 45 |         parts = line.split()
 46 |         if len(parts) == 3:
 47 |             start_time, end_time, kana_sequence = parts
 48 |             phoneme_sequence = convert_kana_sequence_to_phonemes(kana_sequence)
 49 |             converted_lines.append(f"{start_time} {end_time} {phoneme_sequence}")
 50 | 
 51 |     converted_lab_content = '\n'.join(converted_lines)
 52 | 
 53 |     with open(input_path, 'w', encoding='utf-8') as lab_file:
 54 |         lab_file.write(converted_lab_content)
 55 | 
 56 | def browse_labs_directory():
 57 |     directory = filedialog.askdirectory()
 58 |     if directory:
 59 |         labs_directory_entry.delete(0, tk.END)
 60 |         labs_directory_entry.insert(0, directory)
 61 | 
 62 | def convert_labs():
 63 |     labs_directory = labs_directory_entry.get()
 64 | 
 65 |     if not os.path.exists(labs_directory):
 66 |         messagebox.showerror("Error", "LABs directory does not exist.")
 67 |         return
 68 | 
 69 |     for filename in os.listdir(labs_directory):
 70 |         if filename.endswith(".lab"):
 71 |             input_path = os.path.join(labs_directory, filename)
 72 |             process_lab_file(input_path)
 73 | 
 74 |     # Create a text file to store unknown kana characters
 75 |     unknown_kana_file_path = os.path.join(script_directory, 'unknown_kana.txt')
 76 |     with open(unknown_kana_file_path, 'w', encoding='utf-8') as unknown_kana_file:
 77 |         for kana in unknown_kana:
 78 |             unknown_kana_file.write(kana + '\n')
 79 | 
 80 |     messagebox.showinfo("Success", "Conversion complete. Unknown kana characters saved to 'unknown_kana.txt'.")
 81 | 
 82 | # Create the main application window
 83 | root = tk.Tk()
 84 | root.title("Kana to Phonemes converter (lab)")
 85 | 
 86 | # Import the tcl file
 87 | root.tk.call("source", "./Forest-ttk-theme-1.0/forest-dark.tcl")
 88 | 
 89 | # Set the theme with the theme_use method
 90 | style = ttk.Style()
 91 | style.theme_use("forest-dark")
 92 | 
 93 | # Create a frame for the input fields
 94 | input_frame = ttk.Frame(root, padding=10)
 95 | input_frame.grid(row=0, column=0, padx=10, pady=10, sticky='w')
 96 | 
 97 | # LABs directory
 98 | labs_directory_label = ttk.Label(input_frame, text='LABs Directory:')
 99 | labs_directory_label.grid(row=0, column=0, sticky='w')
100 | 
101 | labs_directory_entry = ttk.Entry(input_frame, width=40)
102 | labs_directory_entry.grid(row=0, column=1, padx=(5, 0), sticky='w')
103 | 
104 | labs_directory_button = ttk.Button(input_frame, text='Browse', command=browse_labs_directory)
105 | labs_directory_button.grid(row=0, column=2, padx=(5, 0), sticky='w')
106 | 
107 | # Convert button
108 | convert_button = ttk.Button(root, text='Convert LABs', command=convert_labs)
109 | convert_button.grid(row=1, column=0, padx=10, pady=10)
110 | 
111 | # Start the GUI application
112 | root.mainloop()
113 | 


--------------------------------------------------------------------------------
/hiragana.json:
--------------------------------------------------------------------------------
   1 | [
   2 |   {
   3 |     "kana": "あ",
   4 |     "romaji": "a",
   5 |     "phoneme": "a",
   6 |     "type": "gojuuon"
   7 |   },
   8 |   {
   9 |     "kana": "い",
  10 |     "romaji": "i",
  11 |     "phoneme": "i",
  12 |     "type": "gojuuon"
  13 |   },
  14 |   {
  15 |     "kana": "う",
  16 |     "romaji": "u",
  17 |     "phoneme": "M",
  18 |     "type": "gojuuon"
  19 |   },
  20 |   {
  21 |     "kana": "うぃ",
  22 |     "romaji": "wi",
  23 |     "phoneme": "w i",
  24 |     "type": "gojuuon"
  25 |   },
  26 |   {
  27 |     "kana": "うぉ",
  28 |     "romaji": "wo",
  29 |     "phoneme": "w o",
  30 |     "type": "gojuuon"
  31 |   },
  32 |   {
  33 |     "kana": "うぇ",
  34 |     "romaji": "we",
  35 |     "phoneme": "w e",
  36 |     "type": "gojuuon"
  37 |   },
  38 |   {
  39 |     "kana": "え",
  40 |     "romaji": "e",
  41 |     "phoneme": "e",
  42 |     "type": "gojuuon"
  43 |   },
  44 |   {
  45 |     "kana": "お",
  46 |     "romaji": "o",
  47 |     "phoneme": "o",
  48 |     "type": "gojuuon"
  49 |   },
  50 |   {
  51 |     "kana": "か",
  52 |     "romaji": "ka",
  53 |     "phoneme": "k a",
  54 |     "type": "gojuuon"
  55 |   },
  56 |   {
  57 |     "kana": "き",
  58 |     "romaji": "ki",
  59 |     "phoneme": "k' i",
  60 |     "type": "gojuuon"
  61 |   },
  62 |   {
  63 |     "kana": "く",
  64 |     "romaji": "ku",
  65 |     "phoneme": "k M",
  66 |     "type": "gojuuon"
  67 |   },
  68 |   {
  69 |     "kana": "け",
  70 |     "romaji": "ke",
  71 |     "phoneme": "k e",
  72 |     "type": "gojuuon"
  73 |   },
  74 |   {
  75 |     "kana": "こ",
  76 |     "romaji": "ko",
  77 |     "phoneme": "k o",
  78 |     "type": "gojuuon"
  79 |   },
  80 |   {
  81 |     "kana": "さ",
  82 |     "romaji": "sa",
  83 |     "phoneme": "s a",
  84 |     "type": "gojuuon"
  85 |   },
  86 |   {
  87 |     "kana": "し",
  88 |     "romaji": "shi",
  89 |     "phoneme": "S i",
  90 |     "type": "gojuuon"
  91 |   },
  92 |   {
  93 |     "kana": "す",
  94 |     "romaji": "su",
  95 |     "phoneme": "s M",
  96 |     "type": "gojuuon"
  97 |   },
  98 |   {
  99 |     "kana": "せ",
 100 |     "romaji": "se",
 101 |     "phoneme": "s e",
 102 |     "type": "gojuuon"
 103 |   },
 104 |   {
 105 |     "kana": "そ",
 106 |     "romaji": "so",
 107 |     "phoneme": "s o",
 108 |     "type": "gojuuon"
 109 |   },
 110 |   {
 111 |     "kana": "た",
 112 |     "romaji": "ta",
 113 |     "phoneme": "t a",
 114 |     "type": "gojuuon"
 115 |   },
 116 |   {
 117 |     "kana": "ち",
 118 |     "romaji": "chi",
 119 |     "phoneme": "tS i",
 120 |     "type": "gojuuon"
 121 |   },
 122 |   {
 123 |     "kana": "つ",
 124 |     "romaji": "tsu",
 125 |     "phoneme": "tS M",
 126 |     "type": "gojuuon"
 127 |   },
 128 |   {
 129 |     "kana": "て",
 130 |     "romaji": "te",
 131 |     "phoneme": "t e",
 132 |     "type": "gojuuon"
 133 |   },
 134 |   {
 135 |     "kana": "と",
 136 |     "romaji": "to",
 137 |     "phoneme": "t o",
 138 |     "type": "gojuuon"
 139 |   },
 140 |   {
 141 |     "kana": "な",
 142 |     "romaji": "na",
 143 |     "phoneme": "n a",
 144 |     "type": "gojuuon"
 145 |   },
 146 |   {
 147 |     "kana": "に",
 148 |     "romaji": "ni",
 149 |     "phoneme": "J i",
 150 |     "type": "gojuuon"
 151 |   },
 152 |   {
 153 |     "kana": "ぬ",
 154 |     "romaji": "nu",
 155 |     "phoneme": "n M",
 156 |     "type": "gojuuon"
 157 |   },
 158 |   {
 159 |     "kana": "ね",
 160 |     "romaji": "ne",
 161 |     "phoneme": "n e",
 162 |     "type": "gojuuon"
 163 |   },
 164 |   {
 165 |     "kana": "の",
 166 |     "romaji": "no",
 167 |     "phoneme": "n o",
 168 |     "type": "gojuuon"
 169 |   },
 170 |   {
 171 |     "kana": "は",
 172 |     "romaji": "ha",
 173 |     "phoneme": "h a",
 174 |     "type": "gojuuon"
 175 |   },
 176 |   {
 177 |     "kana": "ひ",
 178 |     "romaji": "hi",
 179 |     "phoneme": "C i",
 180 |     "type": "gojuuon"
 181 |   },
 182 |   {
 183 |     "kana": "ふ",
 184 |     "romaji": "fu",
 185 |     "phoneme": "p\\ M",
 186 |     "type": "gojuuon"
 187 |   },
 188 |   {
 189 |     "kana": "ふぃ",
 190 |     "romaji": "fi",
 191 |     "phoneme": "p\\' i",
 192 |     "type": "gojuuon"
 193 |   },
 194 |   {
 195 |     "kana": "ふぁ",
 196 |     "romaji": "fa",
 197 |     "phoneme": "p\\ a",
 198 |     "type": "gojuuon"
 199 |   },
 200 |   {
 201 |     "kana": "ふぇ",
 202 |     "romaji": "fe",
 203 |     "phoneme": "p\\ e",
 204 |     "type": "gojuuon"
 205 |   },
 206 |   {
 207 |     "kana": "ふゃ",
 208 |     "romaji": "fya",
 209 |     "phoneme": "p\\' a",
 210 |     "type": "gojuuon"
 211 |   },
 212 |   {
 213 |     "kana": "ふゅ",
 214 |     "romaji": "fyu",
 215 |     "phoneme": "p\\' M",
 216 |     "type": "gojuuon"
 217 |   },
 218 |   {
 219 |     "kana": "ふょ",
 220 |     "romaji": "fyo",
 221 |     "phoneme": "p\\' o",
 222 |     "type": "gojuuon"
 223 |   },
 224 |   {
 225 |     "kana": "へ",
 226 |     "romaji": "he",
 227 |     "phoneme": "h e",
 228 |     "type": "gojuuon"
 229 |   },
 230 |   {
 231 |     "kana": "ほ",
 232 |     "romaji": "ho",
 233 |     "phoneme": "h o",
 234 |     "type": "gojuuon"
 235 |   },
 236 |   {
 237 |     "kana": "ま",
 238 |     "romaji": "ma",
 239 |     "phoneme": "m a",
 240 |     "type": "gojuuon"
 241 |   },
 242 |   {
 243 |     "kana": "み",
 244 |     "romaji": "mi",
 245 |     "phoneme": "m' i",
 246 |     "type": "gojuuon"
 247 |   },
 248 |   {
 249 |     "kana": "む",
 250 |     "romaji": "mu",
 251 |     "phoneme": "m M",
 252 |     "type": "gojuuon"
 253 |   },
 254 |   {
 255 |     "kana": "め",
 256 |     "romaji": "me",
 257 |     "phoneme": "m e",
 258 |     "type": "gojuuon"
 259 |   },
 260 |   {
 261 |     "kana": "も",
 262 |     "romaji": "mo",
 263 |     "phoneme": "m o",
 264 |     "type": "gojuuon"
 265 |   },
 266 |   {
 267 |     "kana": "や",
 268 |     "romaji": "ya",
 269 |     "phoneme": "j a",
 270 |     "type": "gojuuon"
 271 |   },
 272 |   {
 273 |     "kana": "ゆ",
 274 |     "romaji": "yu",
 275 |     "phoneme": "j M",
 276 |     "type": "gojuuon"
 277 |   },
 278 |   {
 279 |     "kana": "よ",
 280 |     "romaji": "yo",
 281 |     "phoneme": "j o",
 282 |     "type": "gojuuon"
 283 |   },
 284 |   {
 285 |     "kana": "ら",
 286 |     "romaji": "ra",
 287 |     "phoneme": "4 a",
 288 |     "type": "gojuuon"
 289 |   },
 290 |   {
 291 |     "kana": "り",
 292 |     "romaji": "ri",
 293 |     "phoneme": "4' i",
 294 |     "type": "gojuuon"
 295 |   },
 296 |   {
 297 |     "kana": "る",
 298 |     "romaji": "ru",
 299 |     "phoneme": "4 M",
 300 |     "type": "gojuuon"
 301 |   },
 302 |   {
 303 |     "kana": "れ",
 304 |     "romaji": "re",
 305 |     "phoneme": "4 e",
 306 |     "type": "gojuuon"
 307 |   },
 308 |   {
 309 |     "kana": "ろ",
 310 |     "romaji": "ro",
 311 |     "phoneme": "4 o",
 312 |     "type": "gojuuon"
 313 |   },
 314 |   {
 315 |     "kana": "わ",
 316 |     "romaji": "wa",
 317 |     "phoneme": "w a",
 318 |     "type": "gojuuon"
 319 |   },
 320 |   {
 321 |     "kana": "を",
 322 |     "romaji": "wo",
 323 |     "phoneme": "w o",
 324 |     "type": "gojuuon"
 325 |   },
 326 |   {
 327 |     "kana": "ん",
 328 |     "romaji": "n",
 329 |     "phoneme": "N",
 330 |     "type": "gojuuon"
 331 |   },
 332 |   {
 333 |     "kana": "が",
 334 |     "romaji": "ga",
 335 |     "phoneme": "g a",
 336 |     "type": "dakuon"
 337 |   },
 338 |   {
 339 |     "kana": "ぎ",
 340 |     "romaji": "gi",
 341 |     "phoneme": "g' i",
 342 |     "type": "dakuon"
 343 |   },
 344 |   {
 345 |     "kana": "ぐ",
 346 |     "romaji": "gu",
 347 |     "phoneme": "g M",
 348 |     "type": "dakuon"
 349 |   },
 350 |   {
 351 |     "kana": "げ",
 352 |     "romaji": "ge",
 353 |     "phoneme": "g e",
 354 |     "type": "dakuon"
 355 |   },
 356 |   {
 357 |     "kana": "ご",
 358 |     "romaji": "go",
 359 |     "phoneme": "g o",
 360 |     "type": "dakuon"
 361 |   },
 362 |   {
 363 |     "kana": "ざ",
 364 |     "romaji": "za",
 365 |     "phoneme": "dz a",
 366 |     "type": "dakuon"
 367 |   },
 368 |   {
 369 |     "kana": "じ",
 370 |     "romaji": "ji",
 371 |     "phoneme": "dZ i",
 372 |     "type": "dakuon"
 373 |   },
 374 |   {
 375 |     "kana": "ず",
 376 |     "romaji": "zu",
 377 |     "phoneme": "dz M",
 378 |     "type": "dakuon"
 379 |   },
 380 |   {
 381 |     "kana": "ぜ",
 382 |     "romaji": "ze",
 383 |     "phoneme": "dz e",
 384 |     "type": "dakuon"
 385 |   },
 386 |   {
 387 |     "kana": "ぞ",
 388 |     "romaji": "zo",
 389 |     "phoneme": "dz o",
 390 |     "type": "dakuon"
 391 |   },
 392 |   {
 393 |     "kana": "だ",
 394 |     "romaji": "da",
 395 |     "phoneme": "d a",
 396 |     "type": "dakuon"
 397 |   },
 398 |   {
 399 |     "kana": "ぢ",
 400 |     "romaji": "ji",
 401 |     "phoneme": "dZ i",
 402 |     "type": "dakuon"
 403 |   },
 404 |   {
 405 |     "kana": "づ",
 406 |     "romaji": "zu",
 407 |     "phoneme": "dz M",
 408 |     "type": "dakuon"
 409 |   },
 410 |   {
 411 |     "kana": "で",
 412 |     "romaji": "de",
 413 |     "phoneme": "d e",
 414 |     "type": "dakuon"
 415 |   },
 416 |   {
 417 |     "kana": "ど",
 418 |     "romaji": "do",
 419 |     "phoneme": "d o",
 420 |     "type": "dakuon"
 421 |   },
 422 |   {
 423 |     "kana": "ば",
 424 |     "romaji": "ba",
 425 |     "phoneme": "b a",
 426 |     "type": "dakuon"
 427 |   },
 428 |   {
 429 |     "kana": "び",
 430 |     "romaji": "bi",
 431 |     "phoneme": "b' i",
 432 |     "type": "dakuon"
 433 |   },
 434 |   {
 435 |     "kana": "ぶ",
 436 |     "romaji": "bu",
 437 |     "phoneme": "n M",
 438 |     "type": "dakuon"
 439 |   },
 440 |   {
 441 |     "kana": "べ",
 442 |     "romaji": "be",
 443 |     "phoneme": "b e",
 444 |     "type": "dakuon"
 445 |   },
 446 |   {
 447 |     "kana": "ぼ",
 448 |     "romaji": "bo",
 449 |     "phoneme": "b o",
 450 |     "type": "dakuon"
 451 |   },
 452 |   {
 453 |     "kana": "ぱ",
 454 |     "romaji": "pa",
 455 |     "phoneme": "p a",
 456 |     "type": "handakuon"
 457 |   },
 458 |   {
 459 |     "kana": "ぴ",
 460 |     "romaji": "pi",
 461 |     "phoneme": "p' i",
 462 |     "type": "handakuon"
 463 |   },
 464 |   {
 465 |     "kana": "ぷ",
 466 |     "romaji": "pu",
 467 |     "phoneme": "p M",
 468 |     "type": "handakuon"
 469 |   },
 470 |   {
 471 |     "kana": "ぺ",
 472 |     "romaji": "pe",
 473 |     "phoneme": "p e",
 474 |     "type": "handakuon"
 475 |   },
 476 |   {
 477 |     "kana": "ぽ",
 478 |     "romaji": "po",
 479 |     "phoneme": "p o",
 480 |     "type": "handakuon"
 481 |   },
 482 |   {
 483 |     "kana": "いぇ",
 484 |     "romaji": "ye",
 485 |     "phoneme": "j e",
 486 |     "type": "handakuon"
 487 |   },
 488 |   {
 489 |     "kana": "c",
 490 |     "romaji": "(pause)",
 491 |     "phoneme": "Sil",
 492 |     "type": "sokuon"
 493 |   },
 494 |   {
 495 |     "kana": "きゃ",
 496 |     "romaji": "kya",
 497 |     "phoneme": "k' a",
 498 |     "type": "youon"
 499 |   },
 500 |   {
 501 |     "kana": "きゅ",
 502 |     "romaji": "kyu",
 503 |     "phoneme": "k' M",
 504 |     "type": "youon"
 505 |   },
 506 |   {
 507 |     "kana": "きょ",
 508 |     "romaji": "kyo",
 509 |     "phoneme": "k' o",
 510 |     "type": "youon"
 511 |   },
 512 |   {
 513 |     "kana": "きぇ",
 514 |     "romaji": "kye",
 515 |     "phoneme": "k' e",
 516 |     "type": "youon"
 517 |   },
 518 |   {
 519 |     "kana": "しゃ",
 520 |     "romaji": "sha",
 521 |     "phoneme": "S a",
 522 |     "type": "youon"
 523 |   },
 524 |   {
 525 |     "kana": "しゅ",
 526 |     "romaji": "shu",
 527 |     "phoneme": "S M",
 528 |     "type": "youon"
 529 |   },
 530 |   {
 531 |     "kana": "しょ",
 532 |     "romaji": "sho",
 533 |     "phoneme": "S o",
 534 |     "type": "youon"
 535 |   },
 536 |   {
 537 |     "kana": "ちゃ",
 538 |     "romaji": "cha",
 539 |     "phoneme": "tS a",
 540 |     "type": "youon"
 541 |   },
 542 |   {
 543 |     "kana": "ちゅ",
 544 |     "romaji": "chu",
 545 |     "phoneme": "tS M",
 546 |     "type": "youon"
 547 |   },
 548 |   {
 549 |     "kana": "ちょ",
 550 |     "romaji": "cho",
 551 |     "phoneme": "tS o",
 552 |     "type": "youon"
 553 |   },
 554 |   {
 555 |     "kana": "にゃ",
 556 |     "romaji": "nya",
 557 |     "phoneme": "J a",
 558 |     "type": "youon"
 559 |   },
 560 |   {
 561 |     "kana": "にゅ",
 562 |     "romaji": "nyu",
 563 |     "phoneme": "J M",
 564 |     "type": "youon"
 565 |   },
 566 |   {
 567 |     "kana": "にょ",
 568 |     "romaji": "nyo",
 569 |     "phoneme": "J o",
 570 |     "type": "youon"
 571 |   },
 572 |   {
 573 |     "kana": "ひゃ",
 574 |     "romaji": "hya",
 575 |     "phoneme": "C a",
 576 |     "type": "youon"
 577 |   },
 578 |   {
 579 |     "kana": "ひゅ",
 580 |     "romaji": "hyu",
 581 |     "phoneme": "C M",
 582 |     "type": "youon"
 583 |   },
 584 |   {
 585 |     "kana": "ひょ",
 586 |     "romaji": "hyo",
 587 |     "phoneme": "C o",
 588 |     "type": "youon"
 589 |   },
 590 |   {
 591 |     "kana": "みゃ",
 592 |     "romaji": "mya",
 593 |     "phoneme": "m' a",
 594 |     "type": "youon"
 595 |   },
 596 |   {
 597 |     "kana": "みゅ",
 598 |     "romaji": "myu",
 599 |     "phoneme": "m' M",
 600 |     "type": "youon"
 601 |   },
 602 |   {
 603 |     "kana": "みょ",
 604 |     "romaji": "myo",
 605 |     "phoneme": "m' o",
 606 |     "type": "youon"
 607 |   },
 608 |   {
 609 |     "kana": "りゃ",
 610 |     "romaji": "rya",
 611 |     "phoneme": "4' a",
 612 |     "type": "youon"
 613 |   },
 614 |   {
 615 |     "kana": "りゅ",
 616 |     "romaji": "ryu",
 617 |     "phoneme": "4' M",
 618 |     "type": "youon"
 619 |   },
 620 |   {
 621 |     "kana": "りょ",
 622 |     "romaji": "ryo",
 623 |     "phoneme": "4' o",
 624 |     "type": "youon"
 625 |   },
 626 |   {
 627 |     "kana": "りぇ",
 628 |     "romaji": "rye",
 629 |     "phoneme": "4' e",
 630 |     "type": "youon"
 631 |   },
 632 | 
 633 |   {
 634 |     "kana": "ぎゃ",
 635 |     "romaji": "gya",
 636 |     "phoneme": "g' a",
 637 |     "type": "youon"
 638 |   },
 639 |   {
 640 |     "kana": "ぎゅ",
 641 |     "romaji": "gyu",
 642 |     "phoneme": "g' M",
 643 |     "type": "youon"
 644 |   },
 645 |   {
 646 |     "kana": "ぎょ",
 647 |     "romaji": "gyo",
 648 |     "phoneme": "g' o",
 649 |     "type": "youon"
 650 |   },
 651 |   {
 652 |     "kana": "じゃ",
 653 |     "romaji": "ja",
 654 |     "phoneme": "dZ a",
 655 |     "type": "youon"
 656 |   },
 657 |   {
 658 |     "kana": "じゅ",
 659 |     "romaji": "ju",
 660 |     "phoneme": "dZ M",
 661 |     "type": "youon"
 662 |   },
 663 |   {
 664 |     "kana": "じょ",
 665 |     "romaji": "jo",
 666 |     "phoneme": "dZ o",
 667 |     "type": "youon"
 668 |   },
 669 |   {
 670 |     "kana": "びゃ",
 671 |     "romaji": "bya",
 672 |     "phoneme": "b' a",
 673 |     "type": "youon"
 674 |   },
 675 |   {
 676 |     "kana": "びゅ",
 677 |     "romaji": "byu",
 678 |     "phoneme": "b' M",
 679 |     "type": "youon"
 680 |   },
 681 |   {
 682 |     "kana": "びょ",
 683 |     "romaji": "byo",
 684 |     "phoneme": "b' o",
 685 |     "type": "youon"
 686 |   },
 687 |   {
 688 |     "kana": "ぴゃ",
 689 |     "romaji": "pya",
 690 |     "phoneme": "p' a",
 691 |     "type": "youon"
 692 |   },
 693 |   {
 694 |     "kana": "ぴゅ",
 695 |     "romaji": "pyu",
 696 |     "phoneme": "p' M",
 697 |     "type": "youon"
 698 |   },
 699 |   {
 700 |     "kana": "ぴょ",
 701 |     "romaji": "pyo",
 702 |     "phoneme": "p' o",
 703 |     "type": "youon"
 704 |   },
 705 |   {
 706 |     "kana": "ヴぁ",
 707 |     "romaji": "va",
 708 |     "phoneme": "v' a",
 709 |     "type": "youon"
 710 |   },
 711 |   {
 712 |     "kana": "ヴぃ",
 713 |     "romaji": "vi",
 714 |     "phoneme": "v' i",
 715 |     "type": "youon"
 716 |   },
 717 |   {
 718 |     "kana": "ヴ",
 719 |     "romaji": "vu",
 720 |     "phoneme": "v M",
 721 |     "type": "youon"
 722 |   },
 723 |   {
 724 |     "kana": "ヴぇ",
 725 |     "romaji": "ve",
 726 |     "phoneme": "v' e",
 727 |     "type": "youon"
 728 |   },
 729 |   {
 730 |     "kana": "ヴぉ",
 731 |     "romaji": "vo",
 732 |     "phoneme": "v' o",
 733 |     "type": "youon"
 734 |   },
 735 |   {
 736 |     "kana": "てぃ",
 737 |     "romaji": "ti",
 738 |     "phoneme": "t' i",
 739 |     "type": "youon"
 740 |   },
 741 |   {
 742 |     "kana": "とぅ",
 743 |     "romaji": "tu",
 744 |     "phoneme": "t' M",
 745 |     "type": "youon"
 746 |   },
 747 |   {
 748 |     "kana": "ファ",
 749 |     "romaji": "fa",
 750 |     "phoneme": "p\\ a",
 751 |     "type": "youon"
 752 |   },
 753 |   {
 754 |     "kana": "フィ",
 755 |     "romaji": "fi",
 756 |     "phoneme": "p\\' i",
 757 |     "type": "youon"
 758 |   },
 759 |   {
 760 |     "kana": "フェ",
 761 |     "romaji": "fe",
 762 |     "phoneme": "p\\ e",
 763 |     "type": "youon"
 764 |   },
 765 |   {
 766 |     "kana": "フォ",
 767 |     "romaji": "fo",
 768 |     "phoneme": "p\\ o",
 769 |     "type": "youon"
 770 |   },
 771 |   {
 772 |     "kana": "テュ",
 773 |     "romaji": "tyu",
 774 |     "phoneme": "t' M",
 775 |     "type": "youon"
 776 |   },
 777 |   {
 778 |     "kana": "トァ",
 779 |     "romaji": "twa",
 780 |     "phoneme": "t w a",
 781 |     "type": "youon"
 782 |   },
 783 |   {
 784 |     "kana": "トィ",
 785 |     "romaji": "twi",
 786 |     "phoneme": "t w' i",
 787 |     "type": "youon"
 788 |   },
 789 |   {
 790 |     "kana": "トゥ",
 791 |     "romaji": "twu",
 792 |     "phoneme": "t w' M",
 793 |     "type": "youon"
 794 |   },
 795 |   {
 796 |     "kana": "トェ",
 797 |     "romaji": "twe",
 798 |     "phoneme": "t w' e",
 799 |     "type": "youon"
 800 |   },
 801 |   {
 802 |     "kana": "トォ",
 803 |     "romaji": "two",
 804 |     "phoneme": "t w' o",
 805 |     "type": "youon"
 806 |   },
 807 |   {
 808 |     "kana": "でゅ",
 809 |     "romaji": "dyu",
 810 |     "phoneme": "d' M",
 811 |     "type": "youon"
 812 |   },
 813 |   {
 814 |     "kana": "てゅ",
 815 |     "romaji": "tyu",
 816 |     "phoneme": "t' M",
 817 |     "type": "youon"
 818 |   },
 819 |   {
 820 |     "kana": "でぃ",
 821 |     "romaji": "di",
 822 |     "phoneme": "d' i",
 823 |     "type": "youon"
 824 |   },
 825 |   {
 826 |     "kana": "どぅ",
 827 |     "romaji": "du",
 828 |     "phoneme": "d' M",
 829 |     "type": "youon"
 830 |   },
 831 |   {
 832 |     "kana": "ずぃ",
 833 |     "romaji": "zi",
 834 |     "phoneme": "z' i",
 835 |     "type": "youon"
 836 |   },
 837 |   {
 838 |     "kana": "みぇ",
 839 |     "romaji": "mye",
 840 |     "phoneme": "m' e",
 841 |     "type": "youon"
 842 |   },
 843 |   {
 844 |     "kana": "つぉ",
 845 |     "romaji": "tso",
 846 |     "phoneme": "ts o",
 847 |     "type": "youon"
 848 |   },
 849 |   {
 850 |     "kana": "しぇ",
 851 |     "romaji": "she",
 852 |     "phoneme": "S e",
 853 |     "type": "youon"
 854 |   },
 855 |   {
 856 |     "kana": "つぇ",
 857 |     "romaji": "tse",
 858 |     "phoneme": "ts e",
 859 |     "type": "youon"
 860 |   },
 861 |   {
 862 |     "kana": "ぎぇ",
 863 |     "romaji": "gye",
 864 |     "phoneme": "g' e",
 865 |     "type": "youon"
 866 |   },
 867 |   {
 868 |     "kana": "ふぉ",
 869 |     "romaji": "fo",
 870 |     "phoneme": "p\\ o",
 871 |     "type": "youon"
 872 |   },
 873 |   {
 874 |     "kana": "つぃ",
 875 |     "romaji": "tsi",
 876 |     "phoneme": "ts' i",
 877 |     "type": "youon"
 878 |   },
 879 |   {
 880 |     "kana": "ひぇ",
 881 |     "romaji": "hye",
 882 |     "phoneme": "C e",
 883 |     "type": "youon"
 884 |   },
 885 |   {
 886 |     "kana": "ちぇ",
 887 |     "romaji": "che",
 888 |     "phoneme": "tS e",
 889 |     "type": "youon"
 890 |   },
 891 |   {
 892 |     "kana": "びぇ",
 893 |     "romaji": "bye",
 894 |     "phoneme": "b' e",
 895 |     "type": "youon"
 896 |   },
 897 |   {
 898 |     "kana": "つぁ",
 899 |     "romaji": "tsa",
 900 |     "phoneme": "ts a",
 901 |     "type": "youon"
 902 |   },
 903 |   {
 904 |     "kana": "ぴぇ",
 905 |     "romaji": "pye",
 906 |     "phoneme": "p' e",
 907 |     "type": "youon"
 908 |   },
 909 |   {
 910 |     "kana": "すぃ",
 911 |     "romaji": "si",
 912 |     "phoneme": "s' i",
 913 |     "type": "youon"
 914 |   },
 915 |   {
 916 |     "kana": "にぇ",
 917 |     "romaji": "nye",
 918 |     "phoneme": "J e",
 919 |     "type": "youon"
 920 |   },
 921 |   {
 922 |     "kana": "じぇ",
 923 |     "romaji": "je",
 924 |     "phoneme": "dZ e",
 925 |     "type": "youon"
 926 |   },
 927 |   {
 928 |     "kana": "hy",
 929 |     "romaji": "hy",
 930 |     "phoneme": "C I",
 931 |     "type": "youon"
 932 |   },
 933 |   {
 934 |     "kana": "でゃ",
 935 |     "romaji": "dya",
 936 |     "phoneme": "d' a",
 937 |     "type": "youon"
 938 |   },
 939 |   {
 940 |     "kana": "ン",
 941 |     "romaji": "n",
 942 |     "phoneme": "n",
 943 |     "type": "basic"
 944 |   },
 945 |   {
 946 |     "kana": "k",
 947 |     "romaji": "k",
 948 |     "phoneme": "k",
 949 |     "type": "basic"
 950 |   },
 951 |   {
 952 |     "kana": "びぃ",
 953 |     "romaji": "byi",
 954 |     "phoneme": "b' i",
 955 |     "type": "youon"
 956 |   },
 957 |   {
 958 |     "kana": "てょ",
 959 |     "romaji": "tyo",
 960 |     "phoneme": "t' o",
 961 |     "type": "youon"
 962 |   },
 963 |   {
 964 |     "kana": "h",
 965 |     "romaji": "h",
 966 |     "phoneme": "C",
 967 |     "type": "basic"
 968 |   },
 969 |   {
 970 |     "kana": "n",
 971 |     "romaji": "n",
 972 |     "phoneme": "n",
 973 |     "type": "basic"
 974 |   },
 975 |   {
 976 |     "kana": "ん2",
 977 |     "romaji": "n",
 978 |     "phoneme": "n",
 979 |     "type": "basic"
 980 |   },
 981 |   {
 982 |     "kana": "f",
 983 |     "romaji": "f",
 984 |     "phoneme": "p\\",
 985 |     "type": "basic"
 986 |   },
 987 |   {
 988 |     "kana": "j",
 989 |     "romaji": "j",
 990 |     "phoneme": "dZ",
 991 |     "type": "basic"
 992 |   },
 993 |   {
 994 |     "kana": "ry",
 995 |     "romaji": "ry",
 996 |     "phoneme": "J I",
 997 |     "type": "youon"
 998 |   },
 999 |   {
1000 |     "kana": "m",
1001 |     "romaji": "m",
1002 |     "phoneme": "m",
1003 |     "type": "basic"
1004 |   },
1005 |   {
1006 |     "kana": "dh",
1007 |     "romaji": "dh",
1008 |     "phoneme": "D",
1009 |     "type": "basic"
1010 |   },
1011 |   {
1012 |     "kana": "い2",
1013 |     "romaji": "i",
1014 |     "phoneme": "i",
1015 |     "type": "basic"
1016 |   },
1017 |   {
1018 |     "kana": "w",
1019 |     "romaji": "w",
1020 |     "phoneme": "w",
1021 |     "type": "basic"
1022 |   },
1023 |   {
1024 |     "kana": "v",
1025 |     "romaji": "v",
1026 |     "phoneme": "v",
1027 |     "type": "basic"
1028 |   },
1029 |   {
1030 |     "kana": "お2",
1031 |     "romaji": "o",
1032 |     "phoneme": "o",
1033 |     "type": "basic"
1034 |   },
1035 |   {
1036 |     "kana": "sh",
1037 |     "romaji": "sh",
1038 |     "phoneme": "S",
1039 |     "type": "basic"
1040 |   },
1041 |   {
1042 |     "kana": "s",
1043 |     "romaji": "s",
1044 |     "phoneme": "s",
1045 |     "type": "basic"
1046 |   },
1047 |   {
1048 |     "kana": "by",
1049 |     "romaji": "by",
1050 |     "phoneme": "b I",
1051 |     "type": "youon"
1052 |   },
1053 |   {
1054 |     "kana": "ts",
1055 |     "romaji": "ts",
1056 |     "phoneme": "ts",
1057 |     "type": "basic"
1058 |   },
1059 |   {
1060 |     "kana": "my",
1061 |     "romaji": "my",
1062 |     "phoneme": "m I",
1063 |     "type": "youon"
1064 |   },
1065 |   {
1066 |     "kana": "t",
1067 |     "romaji": "t",
1068 |     "phoneme": "t",
1069 |     "type": "basic"
1070 |   },
1071 |   {
1072 |     "kana": "r",
1073 |     "romaji": "r",
1074 |     "phoneme": "4",
1075 |     "type": "basic"
1076 |   },
1077 |   {
1078 |     "kana": "ty",
1079 |     "romaji": "ty",
1080 |     "phoneme": "tS",
1081 |     "type": "basic"
1082 |   },
1083 |   {
1084 |     "kana": "あ2",
1085 |     "romaji": "a",
1086 |     "phoneme": "a",
1087 |     "type": "basic"
1088 |   },
1089 |   {
1090 |     "kana": "b",
1091 |     "romaji": "b",
1092 |     "phoneme": "b",
1093 |     "type": "basic"
1094 |   },
1095 |   {
1096 |     "kana": "ny",
1097 |     "romaji": "ny",
1098 |     "phoneme": "J",
1099 |     "type": "basic"
1100 |   },
1101 |   {
1102 |     "kana": "ヴゅ",
1103 |     "romaji": "vu",
1104 |     "phoneme": "v M",
1105 |     "type": "youon"
1106 |   },
1107 |   {
1108 |     "kana": "ky",
1109 |     "romaji": "ky",
1110 |     "phoneme": "k I",
1111 |     "type": "youon"
1112 |   },
1113 |   {
1114 |     "kana": "t2",
1115 |     "romaji": "t",
1116 |     "phoneme": "t",
1117 |     "type": "basic"
1118 |   },
1119 |   {
1120 |     "kana": "でょ",
1121 |     "romaji": "dyo",
1122 |     "phoneme": "d' o",
1123 |     "type": "youon"
1124 |   },
1125 |   {
1126 |     "kana": "py",
1127 |     "romaji": "py",
1128 |     "phoneme": "p'",
1129 |     "type": "youon"
1130 |   },
1131 |   {
1132 |     "kana": "ch",
1133 |     "romaji": "ch",
1134 |     "phoneme": "tS",
1135 |     "type": "basic"
1136 |   },
1137 |   {
1138 |     "kana": "吸",
1139 |     "romaji": "kyu",
1140 |     "phoneme": "Asp",
1141 |     "type": "youon"
1142 |   },
1143 |   {
1144 |     "kana": "p",
1145 |     "romaji": "p",
1146 |     "phoneme": "p",
1147 |     "type": "basic"
1148 |   },
1149 |   {
1150 |     "kana": "y",
1151 |     "romaji": "y",
1152 |     "phoneme": "j",
1153 |     "type": "basic"
1154 |   },
1155 |   {
1156 |     "kana": "z",
1157 |     "romaji": "z",
1158 |     "phoneme": "z",
1159 |     "type": "basic"
1160 |   },
1161 |   {
1162 |     "kana": "d",
1163 |     "romaji": "d",
1164 |     "phoneme": "d",
1165 |     "type": "basic"
1166 |   },
1167 |   {
1168 |     "kana": "gy",
1169 |     "romaji": "gy",
1170 |     "phoneme": "g'",
1171 |     "type": "youon"
1172 |   },
1173 |   {
1174 |     "kana": "・",
1175 |     "romaji": "?",
1176 |     "phoneme": "?",
1177 |     "type": "basic"
1178 |   },
1179 |   {
1180 |     "kana": "g",
1181 |     "romaji": "g",
1182 |     "phoneme": "g",
1183 |     "type": "basic"
1184 |   },
1185 |   {
1186 |     "kana": "う2",
1187 |     "romaji": "u",
1188 |     "phoneme": "M",
1189 |     "type": "basic"
1190 |   },
1191 |   {
1192 |     "kana": "え2",
1193 |     "romaji": "e",
1194 |     "phoneme": "e",
1195 |     "type": "basic"
1196 |   },
1197 |   {
1198 |     "kana": "てゃ",
1199 |     "romaji": "tya",
1200 |     "phoneme": "t' a",
1201 |     "type": "youon"
1202 |   },
1203 |   {
1204 |     "kana": "w",
1205 |     "romaji": "w",
1206 |     "phoneme": "w",
1207 |     "type": "basic"
1208 |   },
1209 |   {
1210 |     "kana": "b",
1211 |     "romaji": "b",
1212 |     "phoneme": "b",
1213 |     "type": "basic"
1214 |   },
1215 |   {
1216 |     "kana": "v",
1217 |     "romaji": "v",
1218 |     "phoneme": "v",
1219 |     "type": "basic"
1220 |   },
1221 |   {
1222 |     "kana": "d",
1223 |     "romaji": "d",
1224 |     "phoneme": "d",
1225 |     "type": "basic"
1226 |   },
1227 |   {
1228 |     "kana": "g",
1229 |     "romaji": "g",
1230 |     "phoneme": "g",
1231 |     "type": "basic"
1232 |   },
1233 |   {
1234 |     "kana": "s",
1235 |     "romaji": "s",
1236 |     "phoneme": "s",
1237 |     "type": "basic"
1238 |   },
1239 |   {
1240 |     "kana": "p",
1241 |     "romaji": "p",
1242 |     "phoneme": "p",
1243 |     "type": "basic"
1244 |   },
1245 |   {
1246 |     "kana": "n",
1247 |     "romaji": "n",
1248 |     "phoneme": "n",
1249 |     "type": "basic"
1250 |   },
1251 |   {
1252 |     "kana": "t",
1253 |     "romaji": "t",
1254 |     "phoneme": "t",
1255 |     "type": "basic"
1256 |   },
1257 |   {
1258 |     "kana": "z",
1259 |     "romaji": "z",
1260 |     "phoneme": "z",
1261 |     "type": "basic"
1262 |   },
1263 |   {
1264 |     "kana": "m",
1265 |     "romaji": "m",
1266 |     "phoneme": "m",
1267 |     "type": "basic"
1268 |   },
1269 |   {
1270 |     "kana": "ts",
1271 |     "romaji": "ts",
1272 |     "phoneme": "ts",
1273 |     "type": "basic"
1274 |   },
1275 |   {
1276 |     "kana": "k",
1277 |     "romaji": "k",
1278 |     "phoneme": "k",
1279 |     "type": "basic"
1280 |   }
1281 | ]


--------------------------------------------------------------------------------
/kiritan_script_GUI.py:
--------------------------------------------------------------------------------
  1 | import os
  2 | import argparse
  3 | import tkinter as tk
  4 | from tkinter import ttk
  5 | from tkinter import filedialog
  6 | from tkinter import messagebox
  7 | 
  8 | def load_segments(seg_file):
  9 |     segments = []
 10 |     in_segment_section = False
 11 | 
 12 |     with open(seg_file, 'r') as file:
 13 |         for line in file:
 14 |             if line.strip() == '===' or line.strip() == '=================================================':
 15 |                 in_segment_section = True
 16 |                 continue
 17 | 
 18 |             if in_segment_section:
 19 |                 parts = line.strip().split()
 20 |                 if len(parts) >= 3:
 21 |                     phoneme, begin_time, end_time = parts[0], float(parts[1]), float(parts[2])
 22 |                     segments.append((phoneme, begin_time, end_time))
 23 | 
 24 |     return segments
 25 | 
 26 | def transfer_phonemes(seg_folder1, seg_folder2, out_folder):
 27 |     os.makedirs(out_folder, exist_ok=True)
 28 | 
 29 |     seg_files1 = {}
 30 |     seg_files2 = {}
 31 | 
 32 |     for seg_filename1 in os.listdir(seg_folder1):
 33 |         if seg_filename1.endswith('.seg'):
 34 |             base_name = os.path.splitext(seg_filename1)[0]
 35 |             seg_files1[base_name] = os.path.join(seg_folder1, seg_filename1)
 36 | 
 37 |     for seg_filename2 in os.listdir(seg_folder2):
 38 |         if seg_filename2.endswith('.seg'):
 39 |             base_name = os.path.splitext(seg_filename2)[0]
 40 |             seg_files2[base_name] = os.path.join(seg_folder2, seg_filename2)
 41 | 
 42 |     common_base_names = set(seg_files1.keys()).intersection(seg_files2.keys())
 43 | 
 44 |     for base_name in common_base_names:
 45 |         seg_file1 = seg_files1[base_name]
 46 |         seg_file2 = seg_files2[base_name]
 47 |         out_file = os.path.join(out_folder, base_name + '.seg')
 48 | 
 49 |         segments1 = load_segments(seg_file1)
 50 |         segments2 = load_segments(seg_file2)
 51 | 
 52 |         with open(out_file, 'w') as outfile:
 53 |             outfile.write("nPhonemes {}\n".format(len(segments2)))
 54 |             outfile.write("articulationsAreStationaries 0\n")
 55 |             outfile.write("phoneme\tBeginTime\tEndTime\n")
 56 |             outfile.write("=================================================\n")
 57 | 
 58 |             for i, segment2 in enumerate(segments2):
 59 |                 if i < len(segments1):
 60 |                     phoneme1, begin_time1, end_time1 = segments1[i]
 61 |                     phoneme2, begin_time2, end_time2 = segment2
 62 |                     if phoneme1.strip():
 63 |                         outfile.write(f"{phoneme1}\t{begin_time2:.6f}\t{end_time2:.6f}\n")
 64 |                 else:
 65 |                     phoneme2, begin_time2, end_time2 = segment2
 66 |                     outfile.write(f"{phoneme2}\t{begin_time2:.6f}\t{end_time2:.6f}\n")
 67 | 
 68 |         print(f"Transferred phonemes from {seg_file1} to {seg_file2} and saved in {out_file}")
 69 | 
 70 | def browse_folder1():
 71 |     directory = filedialog.askdirectory()
 72 |     if directory:
 73 |         folder1_entry.delete(0, tk.END)
 74 |         folder1_entry.insert(0, directory)
 75 | 
 76 | def browse_folder2():
 77 |     directory = filedialog.askdirectory()
 78 |     if directory:
 79 |         folder2_entry.delete(0, tk.END)
 80 |         folder2_entry.insert(0, directory)
 81 | 
 82 | def browse_output_folder():
 83 |     directory = filedialog.askdirectory()
 84 |     if directory:
 85 |         output_folder_entry.delete(0, tk.END)
 86 |         output_folder_entry.insert(0, directory)
 87 | 
 88 | def convert_phonemes():
 89 |     folder1 = folder1_entry.get()
 90 |     folder2 = folder2_entry.get()
 91 |     output_folder = output_folder_entry.get()
 92 | 
 93 |     if not os.path.exists(folder1) or not os.path.exists(folder2):
 94 |         messagebox.showerror("Error", "Input folders do not exist.")
 95 |         return
 96 | 
 97 |     if not os.path.exists(output_folder):
 98 |         os.makedirs(output_folder)
 99 | 
100 |     transfer_phonemes(folder1, folder2, output_folder)
101 |     messagebox.showinfo("Success", "Conversion complete.")
102 | 
103 | # Create the main application window
104 | root = tk.Tk()
105 | root.title("Phoneme Transfer")
106 | 
107 | # Import the tcl file
108 | root.tk.call("source", "./Forest-ttk-theme-1.0/forest-dark.tcl")
109 | 
110 | # Set the theme with the theme_use method
111 | style = ttk.Style()
112 | style.theme_use("forest-dark")
113 | 
114 | # Create a frame for the input fields
115 | input_frame = ttk.Frame(root, padding=10)
116 | input_frame.grid(row=0, column=0, padx=10, pady=10, sticky='w')
117 | 
118 | # Folder 1
119 | folder1_label = ttk.Label(input_frame, text='Folder 1 (Donor):')
120 | folder1_label.grid(row=0, column=0, sticky='w')
121 | 
122 | folder1_entry = ttk.Entry(input_frame, width=40)
123 | folder1_entry.grid(row=0, column=1, padx=(5, 0), sticky='w')
124 | 
125 | folder1_button = ttk.Button(input_frame, text='Browse', command=browse_folder1)
126 | folder1_button.grid(row=0, column=2, padx=(5, 0), sticky='w')
127 | 
128 | # Folder 2
129 | folder2_label = ttk.Label(input_frame, text='Folder 2 (Receiver):')
130 | folder2_label.grid(row=1, column=0, sticky='w')
131 | 
132 | folder2_entry = ttk.Entry(input_frame, width=40)
133 | folder2_entry.grid(row=1, column=1, padx=(5, 0), sticky='w')
134 | 
135 | folder2_button = ttk.Button(input_frame, text='Browse', command=browse_folder2)
136 | folder2_button.grid(row=1, column=2, padx=(5, 0), sticky='w')
137 | 
138 | # Output folder
139 | output_folder_label = ttk.Label(input_frame, text='Output Folder:')
140 | output_folder_label.grid(row=2, column=0, sticky='w')
141 | 
142 | output_folder_entry = ttk.Entry(input_frame, width=40)
143 | output_folder_entry.grid(row=2, column=1, padx=(5, 0), sticky='w')
144 | 
145 | output_folder_button = ttk.Button(input_frame, text='Browse', command=browse_output_folder)
146 | output_folder_button.grid(row=2, column=2, padx=(5, 0), sticky='w')
147 | 
148 | # Convert button
149 | convert_button = ttk.Button(root, text='Transfer Phonemes', command=convert_phonemes)
150 | convert_button.grid(row=1, column=0, padx=10, pady=10)
151 | 
152 | # Start the GUI application
153 | root.mainloop()
154 | 


--------------------------------------------------------------------------------
/lab2seg_GUI.py:
--------------------------------------------------------------------------------
  1 | import os
  2 | import tkinter as tk
  3 | from tkinter import ttk
  4 | from tkinter import filedialog
  5 | from tkinter import messagebox
  6 | 
  7 | import argparse
  8 | import re
  9 | 
 10 | def convert_lab_to_seg(input_directory, output_directory):
 11 |     # Create the output directory if it doesn't exist
 12 |     if not os.path.exists(output_directory):
 13 |         os.makedirs(output_directory)
 14 | 
 15 |     # Process each lab file
 16 |     for lab_file_name in os.listdir(input_directory):
 17 |         if lab_file_name.endswith(".lab"):
 18 |             input_lab_file = os.path.join(input_directory, lab_file_name)
 19 |             output_seg_file = os.path.join(output_directory, lab_file_name.replace(".lab", ".seg"))
 20 | 
 21 |             # Initialize variables
 22 |             phoneme_list = []
 23 | 
 24 |             # Open the input lab for reading
 25 |             with open(input_lab_file, 'r') as infile:
 26 |                 lines = infile.readlines()
 27 | 
 28 |             for line in lines:
 29 |                 line = line.strip()
 30 |                 # Use regular expressions to extract phonemes, start times, and end times
 31 |                 match = re.match(r'(\d+)\s+(\d+)\s+(.+)', line)
 32 |                 if match:
 33 |                     start_time = float(match.group(1)) / 1e7  # Convert time to seconds
 34 |                     end_time = float(match.group(2)) / 1e7
 35 |                     phoneme = match.group(3)
 36 | 
 37 |                     # Remove trailing numbers from phonemes (you might remove this)
 38 |                     phoneme = ''.join([c for c in phoneme if not c.isdigit()])
 39 | 
 40 |                     # Replace "R" and "pau" with "Sil" (mostly for arpabet)
 41 |                     if phoneme == "R" or phoneme == "pau":
 42 |                         phoneme = "Sil"
 43 | 
 44 |                     phoneme_list.append((phoneme, start_time, end_time))
 45 | 
 46 |             if phoneme_list:
 47 |                 # .seg writing
 48 |                 with open(output_seg_file, 'w') as outfile:
 49 |                     outfile.write("nPhonemes {}\n".format(len(phoneme_list)))
 50 |                     outfile.write("articulationsAreStationaries 0\n")
 51 |                     outfile.write("phoneme\t\tBeginTime\t\tEndTime\n")
 52 |                     outfile.write("=" * 49 + "\n")
 53 |                     for phoneme, start_time, end_time in phoneme_list:
 54 |                         outfile.write("{}\t\t{:.6f}\t\t{:.6f}\n".format(phoneme, start_time, end_time))
 55 | 
 56 |                 print("Conversion complete for", lab_file_name)
 57 |             else:
 58 |                 print("Skipping empty file:", lab_file_name)
 59 | 
 60 |     print("All conversions complete.")
 61 | 
 62 | def browse_input_directory():
 63 |     directory = filedialog.askdirectory()
 64 |     if directory:
 65 |         input_directory_entry.delete(0, tk.END)
 66 |         input_directory_entry.insert(0, directory)
 67 | 
 68 | def browse_output_directory():
 69 |     directory = filedialog.askdirectory()
 70 |     if directory:
 71 |         output_directory_entry.delete(0, tk.END)
 72 |         output_directory_entry.insert(0, directory)
 73 | 
 74 | def convert_lab_files():
 75 |     input_directory = input_directory_entry.get()
 76 |     output_directory = output_directory_entry.get()
 77 | 
 78 |     if not os.path.exists(input_directory):
 79 |         messagebox.showerror("Error", "Input directory does not exist.")
 80 |         return
 81 | 
 82 |     if not os.path.exists(output_directory):
 83 |         os.makedirs(output_directory)
 84 | 
 85 |     convert_lab_to_seg(input_directory, output_directory)
 86 |     messagebox.showinfo("Success", "Conversion complete.")
 87 | 
 88 | # Create the main application window
 89 | root = tk.Tk()
 90 | root.title("Lab to Seg Converter")
 91 | 
 92 | # Import the tcl file
 93 | root.tk.call("source", "./Forest-ttk-theme-1.0/forest-dark.tcl")
 94 | 
 95 | # Set the theme with the theme_use method
 96 | style = ttk.Style()
 97 | style.theme_use("forest-dark")
 98 | 
 99 | # Create a frame for the input fields
100 | input_frame = ttk.Frame(root, padding=10)
101 | input_frame.grid(row=0, column=0, padx=10, pady=10, sticky='w')
102 | 
103 | # Input directory
104 | input_directory_label = ttk.Label(input_frame, text='Input Directory:')
105 | input_directory_label.grid(row=0, column=0, sticky='w')
106 | 
107 | input_directory_entry = ttk.Entry(input_frame, width=40)
108 | input_directory_entry.grid(row=0, column=1, padx=(5, 0), sticky='w')
109 | 
110 | input_directory_button = ttk.Button(input_frame, text='Browse', command=browse_input_directory)
111 | input_directory_button.grid(row=0, column=2, padx=(5, 0), sticky='w')
112 | 
113 | # Output directory
114 | output_directory_label = ttk.Label(input_frame, text='Output Directory:')
115 | output_directory_label.grid(row=1, column=0, sticky='w')
116 | 
117 | output_directory_entry = ttk.Entry(input_frame, width=40)
118 | output_directory_entry.grid(row=1, column=1, padx=(5, 0), sticky='w')
119 | 
120 | output_directory_button = ttk.Button(input_frame, text='Browse', command=browse_output_directory)
121 | output_directory_button.grid(row=1, column=2, padx=(5, 0), sticky='w')
122 | 
123 | # Convert button
124 | convert_button = ttk.Button(root, text='Convert', command=convert_lab_files)
125 | convert_button.grid(row=1, column=0, padx=10, pady=10)
126 | 
127 | # Start the GUI application
128 | root.mainloop()
129 | 


--------------------------------------------------------------------------------
/phoneme_grabber_GUI.py:
--------------------------------------------------------------------------------
 1 | import tkinter as tk
 2 | from tkinter import ttk
 3 | from tkinter import filedialog
 4 | from tkinter import messagebox
 5 | import subprocess
 6 | 
 7 | # Function to parse an oto.ini file and extract phonemes
 8 | def parse_oto_ini(oto_file):
 9 |     phonemes = set()
10 |     with open(oto_file, 'rb') as file:
11 |         for line in file:
12 |             try:
13 |                 line = line.decode('shift-jis')
14 |             except UnicodeDecodeError:
15 |                 continue
16 |             parts = line.strip().split('=')
17 |             if len(parts) == 2:
18 |                 phoneme_data = parts[1].split(',')[0].strip()
19 |                 phoneme_data = phoneme_data.replace(' ', '\n')  # Replace space with newline
20 |                 phonemes.update(phoneme_data.split('\n'))  # Add individual phonemes to the set
21 |     return phonemes
22 | 
23 | # Function to run the phoneme grabber script
24 | def run_phoneme_grabber():
25 |     oto_file = oto_file_entry.get()
26 |     output_folder = output_folder_entry.get()
27 |     
28 |     try:
29 |         phonemes = parse_oto_ini(oto_file)
30 |         
31 |         output_file = f'{output_folder}/phonemes.txt'
32 |         with open(output_file, 'w', encoding='utf-8') as file:
33 |             for phoneme in sorted(phonemes):
34 |                 file.write(phoneme + '\n')
35 |         
36 |         messagebox.showinfo('Success', f'Phonemes extracted and saved to {output_file}')
37 |     except Exception as e:
38 |         messagebox.showerror('Error', f'An error occurred: {str(e)}')
39 | 
40 | # Create the main application window
41 | root = tk.Tk()
42 | root.title('Phoneme Grabber')
43 | 
44 | # Import the tcl file for the Forest theme
45 | root.tk.call("source", "./Forest-ttk-theme-1.0/forest-dark.tcl")
46 | 
47 | # Set the theme with the theme_use method
48 | style = ttk.Style(root)
49 | style.theme_use("forest-dark")
50 | 
51 | # Create a frame for the input fields
52 | input_frame = ttk.Frame(root, padding=10)
53 | input_frame.grid(row=0, column=0, columnspan=2, padx=10, pady=10, sticky='w')
54 | 
55 | # Oto.ini file input
56 | oto_file_label = ttk.Label(input_frame, text='oto.ini File:')
57 | oto_file_label.grid(row=0, column=0, sticky='w')
58 | 
59 | oto_file_entry = ttk.Entry(input_frame, width=40)
60 | oto_file_entry.grid(row=0, column=1, padx=(5, 0), sticky='w')
61 | 
62 | oto_file_button = ttk.Button(input_frame, text='Browse', command=lambda: browse_file(oto_file_entry))
63 | oto_file_button.grid(row=0, column=2, padx=(5, 0), sticky='w')
64 | 
65 | # Output folder input
66 | output_folder_label = ttk.Label(input_frame, text='Output Folder:')
67 | output_folder_label.grid(row=1, column=0, sticky='w')
68 | 
69 | output_folder_entry = ttk.Entry(input_frame, width=40)
70 | output_folder_entry.grid(row=1, column=1, padx=(5, 0), sticky='w')
71 | 
72 | output_folder_button = ttk.Button(input_frame, text='Browse', command=lambda: browse_directory(output_folder_entry))
73 | output_folder_button.grid(row=1, column=2, padx=(5, 0), sticky='w')
74 | 
75 | # Run button
76 | run_button = ttk.Button(root, text='Run Phoneme Grabber', command=run_phoneme_grabber)
77 | run_button.grid(row=1, column=0, columnspan=2, padx=10, pady=10)
78 | 
79 | # Function to open a file dialog and populate an entry field
80 | def browse_file(entry_field):
81 |     file_path = filedialog.askopenfilename(filetypes=[('oto.ini files', '*.ini')])
82 |     if file_path:
83 |         entry_field.delete(0, tk.END)
84 |         entry_field.insert(0, file_path)
85 | 
86 | # Function to open a directory dialog and populate an entry field
87 | def browse_directory(entry_field):
88 |     folder_path = filedialog.askdirectory()
89 |     if folder_path:
90 |         entry_field.delete(0, tk.END)
91 |         entry_field.insert(0, folder_path)
92 | 
93 | # Start the GUI application
94 | root.mainloop()
95 | 


--------------------------------------------------------------------------------
/phonemes.json:
--------------------------------------------------------------------------------
  1 | [
  2 |   {
  3 |     "kana": "-",
  4 |     "romaji": "Sil",
  5 |     "phoneme": "Sil",
  6 |     "type": "basic"
  7 |   },
  8 |   {
  9 |     "kana": "a",
 10 |     "romaji": "a",
 11 |     "phoneme": "a",
 12 |     "type": "basic"
 13 |   },
 14 |   {
 15 |     "kana": "b",
 16 |     "romaji": "b",
 17 |     "phoneme": "b",
 18 |     "type": "basic"
 19 |   },
 20 |   {
 21 |     "kana": "by",
 22 |     "romaji": "by",
 23 |     "phoneme": "b'",
 24 |     "type": "youon"
 25 |   },
 26 |   {
 27 |     "kana": "ch",
 28 |     "romaji": "ch",
 29 |     "phoneme": "tS",
 30 |     "type": "basic"
 31 |   },
 32 |   {
 33 |     "kana": "d",
 34 |     "romaji": "d",
 35 |     "phoneme": "d",
 36 |     "type": "basic"
 37 |   },
 38 |   {
 39 |     "kana": "e",
 40 |     "romaji": "e",
 41 |     "phoneme": "e",
 42 |     "type": "basic"
 43 |   },
 44 |   {
 45 |     "kana": "g",
 46 |     "romaji": "g",
 47 |     "phoneme": "g",
 48 |     "type": "basic"
 49 |   },
 50 |   {
 51 |     "kana": "gy",
 52 |     "romaji": "gy",
 53 |     "phoneme": "g'",
 54 |     "type": "youon"
 55 |   },
 56 |   {
 57 |     "kana": "h",
 58 |     "romaji": "h",
 59 |     "phoneme": "h",
 60 |     "type": "basic"
 61 |   },
 62 |   {
 63 |     "kana": "hy",
 64 |     "romaji": "hy",
 65 |     "phoneme": "C",
 66 |     "type": "youon"
 67 |   },
 68 |   {
 69 |     "kana": "i",
 70 |     "romaji": "i",
 71 |     "phoneme": "i",
 72 |     "type": "basic"
 73 |   },
 74 |   {
 75 |     "kana": "j",
 76 |     "romaji": "j",
 77 |     "phoneme": "dZ",
 78 |     "type": "basic"
 79 |   },
 80 |   {
 81 |     "kana": "k",
 82 |     "romaji": "k",
 83 |     "phoneme": "k",
 84 |     "type": "basic"
 85 |   },
 86 |   {
 87 |     "kana": "ky",
 88 |     "romaji": "ky",
 89 |     "phoneme": "k'",
 90 |     "type": "youon"
 91 |   },
 92 |   {
 93 |     "kana": "m",
 94 |     "romaji": "m",
 95 |     "phoneme": "m",
 96 |     "type": "basic"
 97 |   },
 98 |   {
 99 |     "kana": "my",
100 |     "romaji": "my",
101 |     "phoneme": "m'",
102 |     "type": "youon"
103 |   },
104 |   {
105 |     "kana": "n",
106 |     "romaji": "n",
107 |     "phoneme": "n",
108 |     "type": "basic"
109 |   },
110 |   {
111 |     "kana": "ny",
112 |     "romaji": "ny",
113 |     "phoneme": "J",
114 |     "type": "basic"
115 |   },
116 |   {
117 |     "kana": "o",
118 |     "romaji": "o",
119 |     "phoneme": "o",
120 |     "type": "basic"
121 |   },
122 |   {
123 |     "kana": "p",
124 |     "romaji": "p",
125 |     "phoneme": "p",
126 |     "type": "basic"
127 |   },
128 |   {
129 |     "kana": "py",
130 |     "romaji": "py",
131 |     "phoneme": "p I",
132 |     "type": "youon"
133 |   },
134 |   {
135 |     "kana": "r",
136 |     "romaji": "r",
137 |     "phoneme": "4",
138 |     "type": "basic"
139 |   },
140 |   {
141 |     "kana": "ry",
142 |     "romaji": "ry",
143 |     "phoneme": "J I",
144 |     "type": "youon"
145 |   },
146 |   {
147 |     "kana": "s",
148 |     "romaji": "s",
149 |     "phoneme": "s",
150 |     "type": "basic"
151 |   },
152 |   {
153 |     "kana": "sh",
154 |     "romaji": "sh",
155 |     "phoneme": "S",
156 |     "type": "basic"
157 |   },
158 |   {
159 |     "kana": "t",
160 |     "romaji": "t",
161 |     "phoneme": "t",
162 |     "type": "basic"
163 |   },
164 |   {
165 |     "kana": "ts",
166 |     "romaji": "ts",
167 |     "phoneme": "ts",
168 |     "type": "basic"
169 |   },
170 |   {
171 |     "kana": "u",
172 |     "romaji": "u",
173 |     "phoneme": "M",
174 |     "type": "basic"
175 |   },
176 |   {
177 |     "kana": "w",
178 |     "romaji": "w",
179 |     "phoneme": "w",
180 |     "type": "basic"
181 |   },
182 |   {
183 |     "kana": "y",
184 |     "romaji": "y",
185 |     "phoneme": "j",
186 |     "type": "basic"
187 |   },
188 |   {
189 |     "kana": "z",
190 |     "romaji": "z",
191 |     "phoneme": "z",
192 |     "type": "basic"
193 |   },
194 |   {
195 |     "kana": "  ",
196 |     "romaji": "iki",
197 |     "phoneme": "br",
198 |     "type": "youon"
199 |   }
200 | ]


--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | pydub==0.25.1
2 | utaupy==1.18.3
3 | 


--------------------------------------------------------------------------------
/trans_convert_GUI.py:
--------------------------------------------------------------------------------
  1 | import tkinter as tk
  2 | from tkinter import ttk
  3 | from tkinter import filedialog
  4 | import os
  5 | import subprocess
  6 | 
  7 | def convert_trans_file(input_file, output_file):
  8 |     with open(input_file, "r") as infile:
  9 |         lines = infile.readlines()
 10 | 
 11 |     output_lines = []
 12 |     top_line = lines[0].strip()  # Keep the top line as is
 13 |     output_lines.append(top_line + "\n")
 14 | 
 15 |     for line in lines[1:-1]:  # Exclude the first and last lines
 16 |         if '[' in line:
 17 |             tokens = line.strip().split(' ')
 18 |             for token in tokens[1:]:
 19 |                 output_lines.append("[" + token)
 20 |                 output_lines.append("\n")
 21 |         else:
 22 |             tokens = line.strip().split('][')
 23 |             for token in tokens:
 24 |                 phonemes = token.split(' ')
 25 |                 if len(phonemes) > 1:
 26 |                     output_lines.append("[" + phonemes[1] + ' ')
 27 |             output_lines.append("\n")
 28 | 
 29 |     with open(output_file, "w") as outfile:
 30 |         outfile.writelines(output_lines)
 31 | 
 32 | def convert_trans_files():
 33 |     input_dir = input_dir_entry.get()
 34 |     output_dir = output_dir_entry.get()
 35 | 
 36 |     if not os.path.exists(output_dir):
 37 |         os.makedirs(output_dir)
 38 | 
 39 |     converted_files = []
 40 | 
 41 |     for filename in os.listdir(input_dir):
 42 |         if filename.endswith(".trans"):
 43 |             input_file = os.path.join(input_dir, filename)
 44 |             output_file = os.path.join(output_dir, filename)
 45 |             convert_trans_file(input_file, output_file)
 46 |             converted_files.append(filename)
 47 | 
 48 |     terminal_output.config(state=tk.NORMAL)
 49 |     if converted_files:
 50 |         terminal_output.insert(tk.END, "Conversion completed for the following files:\n")
 51 |         for file in converted_files:
 52 |             terminal_output.insert(tk.END, file + "\n")
 53 |     else:
 54 |         terminal_output.insert(tk.END, "No .trans files found for conversion.\n")
 55 |     terminal_output.config(state=tk.DISABLED)
 56 | 
 57 | # Create the main application window
 58 | root = tk.Tk()
 59 | root.title("Trans File Converter")
 60 | 
 61 | # Import the tcl file
 62 | root.tk.call("source", "./Forest-ttk-theme-1.0/forest-dark.tcl")
 63 | 
 64 | # Set the theme with the theme_use method
 65 | style = ttk.Style()
 66 | style.theme_use("forest-dark")
 67 | 
 68 | # Make the app responsive
 69 | for i in range(2):
 70 |     root.columnconfigure(index=i, weight=1)
 71 | for i in range(4):
 72 |     root.rowconfigure(index=i, weight=1)
 73 | 
 74 | # Create a Frame for inputs and buttons
 75 | input_frame = ttk.Frame(root)
 76 | input_frame.grid(row=0, column=0, columnspan=2, padx=10, pady=10, sticky="nsew")
 77 | 
 78 | # Input for .trans files directory
 79 | input_dir_label = ttk.Label(input_frame, text="Articulation .trans Input Directory:")
 80 | input_dir_label.grid(row=0, column=0, sticky="w")
 81 | input_dir_entry = ttk.Entry(input_frame, width=40)
 82 | input_dir_entry.grid(row=0, column=1, padx=(0, 5))
 83 | input_dir_browse = ttk.Button(input_frame, text="Browse", command=lambda: browse_directory(input_dir_entry))
 84 | input_dir_browse.grid(row=0, column=2)
 85 | 
 86 | # Input for output directory
 87 | output_dir_label = ttk.Label(input_frame, text="Stationary .trans Output Directory:")
 88 | output_dir_label.grid(row=1, column=0, sticky="w")
 89 | output_dir_entry = ttk.Entry(input_frame, width=40)
 90 | output_dir_entry.grid(row=1, column=1, padx=(0, 5))
 91 | output_dir_browse = ttk.Button(input_frame, text="Browse", command=lambda: browse_directory(output_dir_entry))
 92 | output_dir_browse.grid(row=1, column=2)
 93 | 
 94 | # Convert button
 95 | convert_button = ttk.Button(input_frame, text="Convert .trans Files", command=convert_trans_files)
 96 | convert_button.grid(row=2, column=0, columnspan=3, pady=10)
 97 | 
 98 | # Create a Frame for the terminal output
 99 | output_frame = ttk.Frame(root)
100 | output_frame.grid(row=1, column=0, columnspan=2, padx=10, pady=(0, 10), sticky="nsew")
101 | 
102 | # Terminal output
103 | terminal_output = tk.Text(output_frame, height=10, width=60, state=tk.DISABLED)
104 | terminal_output.grid(row=0, column=0, sticky="nsew")
105 | 
106 | # Function to browse for a directory and update the corresponding entry
107 | def browse_directory(entry_widget):
108 |     directory = filedialog.askdirectory()
109 |     if directory:
110 |         entry_widget.delete(0, tk.END)
111 |         entry_widget.insert(0, directory)
112 | 
113 | # Start the main loop
114 | root.mainloop()
115 | 


--------------------------------------------------------------------------------