Refactor language list

app.py

@@ -16,6 +16,7 @@ from src.config import ApplicationConfig
 from src.hooks.progressListener import ProgressListener
 from src.hooks.subTaskProgressListener import SubTaskProgressListener
 from src.hooks.whisperProgressHook import create_progress_listener_handle
+from src.languages import get_language_names
 from src.modelCache import ModelCache
 from src.source import get_audio_source_collection
 from src.vadParallel import ParallelContext, ParallelTranscription
@@ -40,26 +41,6 @@ MAX_FILE_PREFIX_LENGTH = 17
 # Limit auto_parallel to a certain number of CPUs (specify vad_cpu_cores to get a higher number)
 MAX_AUTO_CPU_CORES = 8
 
-LANGUAGES = [ 
- "English", "Chinese", "German", "Spanish", "Russian", "Korean", 
- "French", "Japanese", "Portuguese", "Turkish", "Polish", "Catalan", 
- "Dutch", "Arabic", "Swedish", "Italian", "Indonesian", "Hindi", 
- "Finnish", "Vietnamese", "Hebrew", "Ukrainian", "Greek", "Malay", 
- "Czech", "Romanian", "Danish", "Hungarian", "Tamil", "Norwegian", 
- "Thai", "Urdu", "Croatian", "Bulgarian", "Lithuanian", "Latin", 
- "Maori", "Malayalam", "Welsh", "Slovak", "Telugu", "Persian", 
- "Latvian", "Bengali", "Serbian", "Azerbaijani", "Slovenian", 
- "Kannada", "Estonian", "Macedonian", "Breton", "Basque", "Icelandic", 
- "Armenian", "Nepali", "Mongolian", "Bosnian", "Kazakh", "Albanian",
- "Swahili", "Galician", "Marathi", "Punjabi", "Sinhala", "Khmer", 
- "Shona", "Yoruba", "Somali", "Afrikaans", "Occitan", "Georgian", 
- "Belarusian", "Tajik", "Sindhi", "Gujarati", "Amharic", "Yiddish", 
- "Lao", "Uzbek", "Faroese", "Haitian Creole", "Pashto", "Turkmen", 
- "Nynorsk", "Maltese", "Sanskrit", "Luxembourgish", "Myanmar", "Tibetan",
- "Tagalog", "Malagasy", "Assamese", "Tatar", "Hawaiian", "Lingala", 
- "Hausa", "Bashkir", "Javanese", "Sundanese"
-]
-
 WHISPER_MODELS = ["tiny", "base", "small", "medium", "large", "large-v1", "large-v2"]
 
 class WhisperTranscriber:
@@ -433,7 +414,7 @@ def create_ui(app_config: ApplicationConfig):
 
     simple_inputs = lambda : [
         gr.Dropdown(choices=whisper_models, value=app_config.default_model_name, label="Model"),
-        gr.Dropdown(choices=sorted(LANGUAGES), label="Language", value=app_config.language),
+        gr.Dropdown(choices=sorted(get_language_names()), label="Language", value=app_config.language),
         gr.Text(label="URL (YouTube, etc.)"),
         gr.File(label="Upload Files", file_count="multiple"),
         gr.Audio(source="microphone", type="filepath", label="Microphone Input"),

cli.py

@@ -6,9 +6,10 @@ import warnings
 import numpy as np
 
 import torch
-from app import LANGUAGES, WhisperTranscriber
+from app import WhisperTranscriber
 from src.config import ApplicationConfig
 from src.download import download_url
+from src.languages import get_language_names
 
 from src.utils import optional_float, optional_int, str2bool
 from src.whisper.whisperFactory import create_whisper_container
@@ -41,7 +42,7 @@ def cli():
                         
     parser.add_argument("--task", type=str, default=app_config.task, choices=["transcribe", "translate"], \
                         help="whether to perform X->X speech recognition ('transcribe') or X->English translation ('translate')")
-    parser.add_argument("--language", type=str, default=app_config.language, choices=sorted(LANGUAGES), \
+    parser.add_argument("--language", type=str, default=app_config.language, choices=sorted(get_language_names()), \
                         help="language spoken in the audio, specify None to perform language detection")
 
     parser.add_argument("--vad", type=str, default=app_config.default_vad, choices=["none", "silero-vad", "silero-vad-skip-gaps", "silero-vad-expand-into-gaps", "periodic-vad"], \

src/languages.py

@@ -0,0 +1,147 @@
+class Language():
+    def __init__(self, code, name):
+        self.code = code
+        self.name = name
+
+    def __str__(self):
+        return "Language(code={}, name={})".format(self.code, self.name)
+
+LANGUAGES = [
+    Language('en', 'English'),
+    Language('zh', 'Chinese'),   
+    Language('de', 'German'),    
+    Language('es', 'Spanish'),   
+    Language('ru', 'Russian'),   
+    Language('ko', 'Korean'),    
+    Language('fr', 'French'),    
+    Language('ja', 'Japanese'),  
+    Language('pt', 'Portuguese'),
+    Language('tr', 'Turkish'),   
+    Language('pl', 'Polish'),    
+    Language('ca', 'Catalan'),   
+    Language('nl', 'Dutch'),     
+    Language('ar', 'Arabic'),
+    Language('sv', 'Swedish'),
+    Language('it', 'Italian'),
+    Language('id', 'Indonesian'),
+    Language('hi', 'Hindi'),
+    Language('fi', 'Finnish'),
+    Language('vi', 'Vietnamese'),
+    Language('he', 'Hebrew'),
+    Language('uk', 'Ukrainian'),
+    Language('el', 'Greek'),
+    Language('ms', 'Malay'),
+    Language('cs', 'Czech'),
+    Language('ro', 'Romanian'),
+    Language('da', 'Danish'),
+    Language('hu', 'Hungarian'),
+    Language('ta', 'Tamil'),
+    Language('no', 'Norwegian'),
+    Language('th', 'Thai'),
+    Language('ur', 'Urdu'),
+    Language('hr', 'Croatian'),
+    Language('bg', 'Bulgarian'),
+    Language('lt', 'Lithuanian'),
+    Language('la', 'Latin'),
+    Language('mi', 'Maori'),
+    Language('ml', 'Malayalam'),
+    Language('cy', 'Welsh'),
+    Language('sk', 'Slovak'),
+    Language('te', 'Telugu'),
+    Language('fa', 'Persian'),
+    Language('lv', 'Latvian'),
+    Language('bn', 'Bengali'),
+    Language('sr', 'Serbian'),
+    Language('az', 'Azerbaijani'),
+    Language('sl', 'Slovenian'),
+    Language('kn', 'Kannada'),
+    Language('et', 'Estonian'),
+    Language('mk', 'Macedonian'),
+    Language('br', 'Breton'),
+    Language('eu', 'Basque'),
+    Language('is', 'Icelandic'),
+    Language('hy', 'Armenian'),
+    Language('ne', 'Nepali'),
+    Language('mn', 'Mongolian'),
+    Language('bs', 'Bosnian'),
+    Language('kk', 'Kazakh'),
+    Language('sq', 'Albanian'),
+    Language('sw', 'Swahili'),
+    Language('gl', 'Galician'),
+    Language('mr', 'Marathi'),
+    Language('pa', 'Punjabi'),
+    Language('si', 'Sinhala'),
+    Language('km', 'Khmer'),
+    Language('sn', 'Shona'),
+    Language('yo', 'Yoruba'),
+    Language('so', 'Somali'),
+    Language('af', 'Afrikaans'),
+    Language('oc', 'Occitan'),
+    Language('ka', 'Georgian'),
+    Language('be', 'Belarusian'),
+    Language('tg', 'Tajik'),
+    Language('sd', 'Sindhi'),
+    Language('gu', 'Gujarati'),
+    Language('am', 'Amharic'),
+    Language('yi', 'Yiddish'),
+    Language('lo', 'Lao'),
+    Language('uz', 'Uzbek'),
+    Language('fo', 'Faroese'),
+    Language('ht', 'Haitian creole'),
+    Language('ps', 'Pashto'),
+    Language('tk', 'Turkmen'),
+    Language('nn', 'Nynorsk'),
+    Language('mt', 'Maltese'),
+    Language('sa', 'Sanskrit'),
+    Language('lb', 'Luxembourgish'),
+    Language('my', 'Myanmar'),
+    Language('bo', 'Tibetan'),
+    Language('tl', 'Tagalog'),
+    Language('mg', 'Malagasy'),
+    Language('as', 'Assamese'),
+    Language('tt', 'Tatar'),
+    Language('haw', 'Hawaiian'),
+    Language('ln', 'Lingala'),
+    Language('ha', 'Hausa'),
+    Language('ba', 'Bashkir'),
+    Language('jw', 'Javanese'),
+    Language('su', 'Sundanese')
+]
+
+_TO_LANGUAGE_CODE = {
+    **{language.code: language for language in LANGUAGES},
+    "burmese": "my",
+    "valencian": "ca",
+    "flemish": "nl",
+    "haitian": "ht",
+    "letzeburgesch": "lb",
+    "pushto": "ps",
+    "panjabi": "pa",
+    "moldavian": "ro",
+    "moldovan": "ro",
+    "sinhalese": "si",
+    "castilian": "es",
+}
+    
+_FROM_LANGUAGE_NAME = {
+    **{language.name.lower(): language for language in LANGUAGES}
+}
+
+def get_language_from_code(language_code, default=None) -> Language:
+    """Return the language name from the language code."""
+    return _TO_LANGUAGE_CODE.get(language_code, default)
+
+def get_language_from_name(language, default=None) -> Language:
+    """Return the language code from the language name."""
+    return _FROM_LANGUAGE_NAME.get(language.lower() if language else None, default)
+
+def get_language_names():
+    """Return a list of language names."""
+    return [language.name for language in LANGUAGES]
+
+if __name__ == "__main__":
+    # Test lookup
+    print(get_language_from_code('en'))
+    print(get_language_from_name('English'))
+    
+    print(get_language_names())

src/whisper/fasterWhisperContainer.py

@@ -4,6 +4,7 @@ from typing import List, Union
 from faster_whisper import WhisperModel, download_model
 from src.config import ModelConfig
 from src.hooks.progressListener import ProgressListener
+from src.languages import get_language_from_name
 from src.modelCache import ModelCache
 from src.whisper.abstractWhisperContainer import AbstractWhisperCallback, AbstractWhisperContainer
 
@@ -179,24 +180,9 @@ class FasterWhisperCallback(AbstractWhisperCallback):
         return [int(token) for token in suppress_tokens.split(",")]
 
     def _lookup_language_code(self, language: str):
-        lookup = {
-            "english": "en", "chinese": "zh", "german": "de", "spanish": "es", "russian": "ru", "korean": "ko",
-            "french": "fr", "japanese": "ja", "portuguese": "pt", "turkish": "tr", "polish": "pl", "catalan": "ca",
-            "dutch": "nl", "arabic": "ar", "swedish": "sv", "italian": "it", "indonesian": "id", "hindi": "hi",
-            "finnish": "fi", "vietnamese": "vi", "hebrew": "he", "ukrainian": "uk", "greek": "el", "malay": "ms",
-            "czech": "cs", "romanian": "ro", "danish": "da", "hungarian": "hu", "tamil": "ta", "norwegian": "no",
-            "thai": "th", "urdu": "ur", "croatian": "hr", "bulgarian": "bg", "lithuanian": "lt", "latin": "la",
-            "maori": "mi", "malayalam": "ml", "welsh": "cy", "slovak": "sk", "telugu": "te", "persian": "fa",
-            "latvian": "lv", "bengali": "bn", "serbian": "sr", "azerbaijani": "az", "slovenian": "sl",
-            "kannada": "kn", "estonian": "et", "macedonian": "mk", "breton": "br", "basque": "eu", "icelandic": "is",
-            "armenian": "hy", "nepali": "ne", "mongolian": "mn", "bosnian": "bs", "kazakh": "kk", "albanian": "sq",
-            "swahili": "sw", "galician": "gl", "marathi": "mr", "punjabi": "pa", "sinhala": "si", "khmer": "km",
-            "shona": "sn", "yoruba": "yo", "somali": "so", "afrikaans": "af", "occitan": "oc", "georgian": "ka",
-            "belarusian": "be", "tajik": "tg", "sindhi": "sd", "gujarati": "gu", "amharic": "am", "yiddish": "yi",
-            "lao": "lo", "uzbek": "uz", "faroese": "fo", "haitian creole": "ht", "pashto": "ps", "turkmen": "tk",
-            "nynorsk": "nn", "maltese": "mt", "sanskrit": "sa", "luxembourgish": "lb", "myanmar": "my", "tibetan": "bo",
-            "tagalog": "tl", "malagasy": "mg", "assamese": "as", "tatar": "tt", "hawaiian": "haw", "lingala": "ln",
-            "hausa": "ha", "bashkir": "ba", "javanese": "jv", "sundanese": "su"
-        }
+        language = get_language_from_name(language)
 
-        return lookup.get(language.lower() if language is not None else None, language)
+        if language is None:
+            raise ValueError("Invalid language: " + language)
+        
+        return language.code