Revert "Merge pull request #43 from ROBERT-MCDOWELL/main"

This reverts commit ad357da, reversing changes made to d6297a5.
DrewThomasson · Nov 16, 2024 · a5925bf · a5925bf
1 parent ad357da
commit a5925bf
Show file tree

Hide file tree

Showing 65 changed files with 174 additions and 189 deletions.
diff --git a/app.py b/app.py
@@ -6,10 +6,9 @@
 import sys
 
 from lib.conf import *
-from lib.lang import language_mapping, default_language_code
+from lib.lang import language_options, default_language_code
 
 script_mode = NATIVE
-share = False
 
 def check_python_version():
     current_version = sys.version_info[:2]  # (major, minor)
@@ -100,10 +99,10 @@ def is_port_in_use(port):
         return s.connect_ex(('0.0.0.0', port)) == 0
 
 def main():
-    global script_mode, share, ebooks_dir
+    global script_mode, ebooks_dir
 
     # Convert the list of languages to a string to display in the help text
-    lang_list_str = ", ".join(list(language_mapping.keys()))
+    language_options_str = ", ".join(language_options)
 
     # Argument parser to handle optional parameters with descriptions
     parser = argparse.ArgumentParser(
@@ -112,21 +111,21 @@ def main():
 Example usage:    
 Windows:
     headless:
-    ebook2audiobook.cmd --headless --ebook 'path_to_ebook' --voice 'path_to_voice' --language en --custom_model 'model.zip'
+    ebook2audiobook.cmd --headless --ebook 'path_to_ebook' --voice 'path_to_voice' --language en --use_custom_model --custom_model 'model.zip' --custom_config config.json --custom_vocab vocab.json
     Graphic Interface:
     ebook2audiobook.cmd
 Linux/Mac:
     headless:
-    ./ebook2audiobook.sh --headless --ebook 'path_to_ebook' --voice 'path_to_voice' --language en --custom_model 'model.zip'
+    ./ebook2audiobook.sh --headless --ebook 'path_to_ebook' --voice 'path_to_voice' --language en --use_custom_model --custom_model 'model.zip' --custom_config config.json --custom_vocab vocab.json
     Graphic Interface:
     ./ebook2audiobook.sh
 """,
         formatter_class=argparse.RawTextHelpFormatter
     )
     options = [
         "--script_mode", "--share", "--headless", "--ebook", "--ebooks_dir",
-        "--voice", "--language", "--device", "--custom_model", 
-        "--custom_model_url", "--temperature",
+        "--voice", "--language", "--device", "--use_custom_model", "--custom_model", 
+        "--custom_config", "--custom_vocab", "--custom_model_url", "--temperature",
         "--length_penalty", "--repetition_penalty", "--top_k", "--top_p", "--speed",
         "--enable_text_splitting", "--version"
     ]
@@ -143,31 +142,37 @@ def main():
     parser.add_argument(options[5], type=str,
                         help="Path to the target voice file for TTS. Optional, uses a default voice if not provided.")
     parser.add_argument(options[6], type=str, default="en",
-                        help=f"Language for the audiobook conversion. Options: {lang_list_str}. Defaults to English (en).")
+                        help=f"Language for the audiobook conversion. Options: {language_options_str}. Defaults to English (en).")
     parser.add_argument(options[7], type=str, default="cpu", choices=["cpu", "gpu"],
                         help=f"Type of processor unit for the audiobook conversion. If not specified: check first if gpu available, if not cpu is selected.")
-    parser.add_argument(options[8], type=str,
-                        help="Path to the custom model file (.pth). Required if using a custom model.")
+    parser.add_argument(options[8], action="store_true",
+                        help="Use a custom TTS model. Defaults to False. Must be True to use custom models.")
     parser.add_argument(options[9], type=str,
+                        help="Path to the custom model file (.pth). Required if using a custom model.")
+    parser.add_argument(options[10], type=str,
+                        help="Path to the custom config file (config.json). Required if using a custom model.")
+    parser.add_argument(options[11], type=str,
+                        help="Path to the custom vocab file (vocab.json). Required if using a custom model.")
+    parser.add_argument(options[12], type=str,
                         help=("URL to download the custom model as a zip file. Optional, but will be used if provided. "
                               "Examples include David Attenborough's model: "
                               "'https://huggingface.co/drewThomasson/xtts_David_Attenborough_fine_tune/resolve/main/Finished_model_files.zip?download=true'. "
                               "More XTTS fine-tunes can be found on my Hugging Face at 'https://huggingface.co/drewThomasson'."))
-    parser.add_argument(options[10], type=float, default=0.65,
+    parser.add_argument(options[13], type=float, default=0.65,
                         help="Temperature for the model. Defaults to 0.65. Higher temperatures lead to more creative outputs.")
-    parser.add_argument(options[11], type=float, default=1.0,
+    parser.add_argument(options[14], type=float, default=1.0,
                         help="A length penalty applied to the autoregressive decoder. Defaults to 1.0. Not applied to custom models.")
-    parser.add_argument(options[12], type=float, default=2.0,
+    parser.add_argument(options[15], type=float, default=2.0,
                         help="A penalty that prevents the autoregressive decoder from repeating itself. Defaults to 2.0.")
-    parser.add_argument(options[13], type=int, default=50,
+    parser.add_argument(options[16], type=int, default=50,
                         help="Top-k sampling. Lower values mean more likely outputs and increased audio generation speed. Defaults to 50.")
-    parser.add_argument(options[14], type=float, default=0.8,
+    parser.add_argument(options[17], type=float, default=0.8,
                         help="Top-p sampling. Lower values mean more likely outputs and increased audio generation speed. Defaults to 0.8.")
-    parser.add_argument(options[15], type=float, default=1.0,
+    parser.add_argument(options[18], type=float, default=1.0,
                         help="Speed factor for the speech generation. Defaults to 1.0.")
-    parser.add_argument(options[16], action="store_true",
+    parser.add_argument(options[19], action="store_true",
                         help="Enable splitting text into sentences. Defaults to False.")
-    parser.add_argument(options[17], action="version",version=f"ebook2audiobook version {version}",
+    parser.add_argument(options[20], action="version",version=f"ebook2audiobook version {version}",
                         help="Show the version of the script and exit")
 
     for arg in sys.argv:
@@ -183,7 +188,6 @@ def main():
         sys.exit(1)
 
     script_mode = args.script_mode if args.script_mode else script_mode
-    share =  args.share if args.share else share
 
     if script_mode == NATIVE:
         check_pkg = check_and_install_requirements(requirements_file)
@@ -232,13 +236,11 @@ def main():
             else:
                 print(f"Error: The directory {ebooks_dir} does not exist.")
                 sys.exit(1)
-
         elif args.ebook:
             progress_status, audiobook_file = convert_ebook(args)
             if audiobook_file is None:
                 print(f"Conversion failed: {progress_status}")
                 sys.exit(1)
-
         else:
             print("Error: In headless mode, you must specify either an ebook file using --ebook or an ebook directory using --ebooks_dir.")
             sys.exit(1)       
@@ -247,7 +249,7 @@ def main():
         allowed_arguments = {'--share', '--script_mode'}
         passed_args_set = {arg for arg in passed_arguments if arg.startswith('--')}
         if passed_args_set.issubset(allowed_arguments):
-             web_interface(script_mode, share)
+             web_interface(args.script_mode, args.share)
         else:
             print("Error: In non-headless mode, no option or only '--share' can be passed")
             sys.exit(1)

diff --git a/ebook2audiobook.cmd b/ebook2audiobook.cmd
@@ -37,7 +37,7 @@ if not exist "%CALIBRE_TEMP_DIR%" (
 
 icacls "%CALIBRE_TEMP_DIR%" /grant Users:(OI)(CI)F /T
 
-for %%A in (%ARGS%) do (
+for %%A in (%*) do (
 	if "%%A"=="%DOCKER_UTILS%" (
 		set "SCRIPT_MODE=%DOCKER_UTILS%"
 		break
@@ -228,7 +228,7 @@ if not "%DOCKER_BUILD_STATUS%"=="0" (
 net session >nul 2>&1
 if %errorlevel% equ 0 (
     echo Restarting in user mode...
-    start "" /b cmd /c "%~f0" %ARGS%
+    start "" /b cmd /c "%~f0" %*
     exit /b
 )
 goto dispatch
@@ -269,7 +269,7 @@ if "%SCRIPT_MODE%"=="%FULL_DOCKER%" (
 		call conda create --prefix %SCRIPT_DIR%\%PYTHON_ENV% python=%PYTHON_VERSION% -y
 		call conda activate %SCRIPT_DIR%\%PYTHON_ENV%
 		call python -m pip install --upgrade pip
-		call python -m pip install --upgrade -r requirements.txt
+		call python -m pip install beautifulsoup4 coqui-tts ebooklib docker "gradio>=4.44.0" mecab mecab-python3 "nltk>=3.8.2" pydub translate tqdm unidic
 		call python -m unidic download
 		call python -m spacy download en_core_web_sm
 		call python -m nltk.downloader punkt_tab

diff --git a/ebook2audiobook.sh b/ebook2audiobook.sh
@@ -212,7 +212,7 @@ function conda_check {
 		source $CONDA_ENV
 		conda activate $SCRIPT_DIR/$PYTHON_ENV
 		python -m pip install --upgrade pip
-		python -m pip install --upgrade -r requirements.txt
+		python -m pip install beautifulsoup4 coqui-tts ebooklib docker "gradio>=4.44.0" mecab mecab-python3 "nltk>=3.8.2" pydub translate tqdm unidic
 		python -m unidic download
 		python -m spacy download en_core_web_sm
 		python -m nltk.downloader punkt_tab

diff --git a/ebooks/test1.epub b/ebooks/test1.epub
diff --git a/ebooks/test2.azw3 b/ebooks/test2.azw3
diff --git a/ebooks/test3.pdf b/ebooks/test3.pdf
diff --git a/ebooks/test4.txt b/ebooks/test4.txt
@@ -0,0 +1 @@
+this is the test four from the result of text file to audiobook conversion.
diff --git a/ebooks/test_ar.azw3 b/ebooks/test_ar.azw3
diff --git a/ebooks/test_ar.txt b/ebooks/test_ar.txt
diff --git a/ebooks/test_cs.azw3 b/ebooks/test_cs.azw3
diff --git a/ebooks/test_cs.txt b/ebooks/test_cs.txt
diff --git a/ebooks/test_da.azw3 b/ebooks/test_da.azw3
diff --git a/ebooks/test_da.txt b/ebooks/test_da.txt
diff --git a/ebooks/test_de.azw3 b/ebooks/test_de.azw3
diff --git a/ebooks/test_de.txt b/ebooks/test_de.txt
diff --git a/ebooks/test_el.azw3 b/ebooks/test_el.azw3
diff --git a/ebooks/test_el.txt b/ebooks/test_el.txt
diff --git a/ebooks/test_en.azw3 b/ebooks/test_en.azw3
diff --git a/ebooks/test_en.txt b/ebooks/test_en.txt
diff --git a/ebooks/test_es.azw3 b/ebooks/test_es.azw3
diff --git a/ebooks/test_es.txt b/ebooks/test_es.txt
diff --git a/ebooks/test_fi.azw3 b/ebooks/test_fi.azw3
diff --git a/ebooks/test_fi.txt b/ebooks/test_fi.txt
diff --git a/ebooks/test_fr.azw3 b/ebooks/test_fr.azw3
diff --git a/ebooks/test_fr.txt b/ebooks/test_fr.txt
diff --git a/ebooks/test_hr.azw3 b/ebooks/test_hr.azw3
diff --git a/ebooks/test_hr.txt b/ebooks/test_hr.txt
diff --git a/ebooks/test_it.azw3 b/ebooks/test_it.azw3
diff --git a/ebooks/test_it.txt b/ebooks/test_it.txt
diff --git a/ebooks/test_ja.azw3 b/ebooks/test_ja.azw3
diff --git a/ebooks/test_ja.txt b/ebooks/test_ja.txt
diff --git a/ebooks/test_ko.azw3 b/ebooks/test_ko.azw3
diff --git a/ebooks/test_ko.txt b/ebooks/test_ko.txt
diff --git a/ebooks/test_nb.azw3 b/ebooks/test_nb.azw3
diff --git a/ebooks/test_nb.txt b/ebooks/test_nb.txt
diff --git a/ebooks/test_nl.azw3 b/ebooks/test_nl.azw3
diff --git a/ebooks/test_nl.txt b/ebooks/test_nl.txt
diff --git a/ebooks/test_pl.azw3 b/ebooks/test_pl.azw3
diff --git a/ebooks/test_pl.txt b/ebooks/test_pl.txt
diff --git a/ebooks/test_pt.azw3 b/ebooks/test_pt.azw3
diff --git a/ebooks/test_pt.txt b/ebooks/test_pt.txt
diff --git a/ebooks/test_ro.azw3 b/ebooks/test_ro.azw3
diff --git a/ebooks/test_ro.txt b/ebooks/test_ro.txt
diff --git a/ebooks/test_ru.azw3 b/ebooks/test_ru.azw3
diff --git a/ebooks/test_ru.txt b/ebooks/test_ru.txt
diff --git a/ebooks/test_sl.azw3 b/ebooks/test_sl.azw3
diff --git a/ebooks/test_sl.txt b/ebooks/test_sl.txt
diff --git a/ebooks/test_sv.azw3 b/ebooks/test_sv.azw3
diff --git a/ebooks/test_sv.txt b/ebooks/test_sv.txt
diff --git a/ebooks/test_zh.azw3 b/ebooks/test_zh.azw3
diff --git a/ebooks/test_zh.txt b/ebooks/test_zh.txt
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		this is the test four from the result of text file to audiobook conversion.