Update app.py

app.py

@@ -26,12 +26,108 @@ import wave
 import contextlib
 from transformers import pipeline
 import psutil
-import shutil
 
 whisper_models = ["tiny", "base", "small", "medium", "large-v1", "large-v2"]
 source_languages = {
     "en": "English",
+    "zh": "Chinese",
+    "de": "German",
+    "es": "Spanish",
+    "ru": "Russian",
+    "ko": "Korean",
+    "fr": "French",
     "ja": "Japanese",
+    "pt": "Portuguese",
+    "tr": "Turkish",
+    "pl": "Polish",
+    "ca": "Catalan",
+    "nl": "Dutch",
+    "ar": "Arabic",
+    "sv": "Swedish",
+    "it": "Italian",
+    "id": "Indonesian",
+    "hi": "Hindi",
+    "fi": "Finnish",
+    "vi": "Vietnamese",
+    "he": "Hebrew",
+    "uk": "Ukrainian",
+    "el": "Greek",
+    "ms": "Malay",
+    "cs": "Czech",
+    "ro": "Romanian",
+    "da": "Danish",
+    "hu": "Hungarian",
+    "ta": "Tamil",
+    "no": "Norwegian",
+    "th": "Thai",
+    "ur": "Urdu",
+    "hr": "Croatian",
+    "bg": "Bulgarian",
+    "lt": "Lithuanian",
+    "la": "Latin",
+    "mi": "Maori",
+    "ml": "Malayalam",
+    "cy": "Welsh",
+    "sk": "Slovak",
+    "te": "Telugu",
+    "fa": "Persian",
+    "lv": "Latvian",
+    "bn": "Bengali",
+    "sr": "Serbian",
+    "az": "Azerbaijani",
+    "sl": "Slovenian",
+    "kn": "Kannada",
+    "et": "Estonian",
+    "mk": "Macedonian",
+    "br": "Breton",
+    "eu": "Basque",
+    "is": "Icelandic",
+    "hy": "Armenian",
+    "ne": "Nepali",
+    "mn": "Mongolian",
+    "bs": "Bosnian",
+    "kk": "Kazakh",
+    "sq": "Albanian",
+    "sw": "Swahili",
+    "gl": "Galician",
+    "mr": "Marathi",
+    "pa": "Punjabi",
+    "si": "Sinhala",
+    "km": "Khmer",
+    "sn": "Shona",
+    "yo": "Yoruba",
+    "so": "Somali",
+    "af": "Afrikaans",
+    "oc": "Occitan",
+    "ka": "Georgian",
+    "be": "Belarusian",
+    "tg": "Tajik",
+    "sd": "Sindhi",
+    "gu": "Gujarati",
+    "am": "Amharic",
+    "yi": "Yiddish",
+    "lo": "Lao",
+    "uz": "Uzbek",
+    "fo": "Faroese",
+    "ht": "Haitian creole",
+    "ps": "Pashto",
+    "tk": "Turkmen",
+    "nn": "Nynorsk",
+    "mt": "Maltese",
+    "sa": "Sanskrit",
+    "lb": "Luxembourgish",
+    "my": "Myanmar",
+    "bo": "Tibetan",
+    "tl": "Tagalog",
+    "mg": "Malagasy",
+    "as": "Assamese",
+    "tt": "Tatar",
+    "haw": "Hawaiian",
+    "ln": "Lingala",
+    "ha": "Hausa",
+    "ba": "Bashkir",
+    "jw": "Javanese",
+    "su": "Sundanese",
 }
 
 source_language_list = [key[0] for key in source_languages.items()]
@@ -46,8 +142,6 @@ pipe = pipeline(
     chunk_length_s=30,
     device=device,
 )
-if os.path.exists('output'):
-    shutil.rmtree('output')
 os.makedirs('output', exist_ok=True)
 pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language=lang, task="transcribe")
 
@@ -349,42 +443,45 @@ with demo:
             with gr.Column():
                 download_transcript.render()
                 transcription_df.render()
-
-    with gr.Tab("Whisper Transcribe Japanese Audio"):
-        gr.Markdown(f'''
-              <div>
-              <h1 style='text-align: center'>Whisper Transcribe Japanese Audio</h1>
-              </div>
-              Transcribe long-form microphone or audio inputs with the click of a button! The fine-tuned
-              checkpoint <a href='https://huggingface.co/{MODEL_NAME}' target='_blank'><b>{MODEL_NAME}</b></a> to transcribe audio files of arbitrary length.
-          ''')
-        microphone = gr.inputs.Audio(source="microphone", type="filepath", optional=True)
-        upload = gr.inputs.Audio(source="upload", type="filepath", optional=True)
-        transcribe_btn = gr.Button("Transcribe Audio")
-        text_output = gr.Textbox()
-        with gr.Row():
-            gr.Markdown('''
-                ### You can test by following examples:
-                ''')
-        examples = gr.Examples(examples=
-                               ["sample1.wav",
-                                "sample2.wav",
-                                ],
-                               label="Examples", inputs=[upload])
-        transcribe_btn.click(transcribe, [microphone, upload], outputs=text_output)
-
-    with gr.Tab("Whisper Transcribe Japanese YouTube"):
-        gr.Markdown(f'''
-              <div>
-              <h1 style='text-align: center'>Whisper Transcribe Japanese YouTube</h1>
-              </div>
-                Transcribe long-form YouTube videos with the click of a button! The fine-tuned checkpoint:
-                <a href='https://huggingface.co/{MODEL_NAME}' target='_blank'><b>{MODEL_NAME}</b></a> to transcribe audio files of arbitrary length.
-            ''')
-        youtube_link = gr.Textbox(label="Youtube url", lines=1, interactive=True)
-        yt_transcribe_btn = gr.Button("Transcribe YouTube")
-        text_output2 = gr.Textbox()
-        html_output = gr.Markdown()
-        yt_transcribe_btn.click(yt_transcribe, [youtube_link], outputs=[html_output, text_output2])
-
-demo.launch(debug=True)
+                system_info.render()
+                gr.Markdown(
+                    '''<center><img src='https://visitor-badge.glitch.me/badge?page_id=WhisperDiarizationSpeakers' alt='visitor badge'><a href="https://opensource.org/licenses/Apache-2.0"><img src='https://img.shields.io/badge/License-Apache_2.0-blue.svg' alt='License: Apache 2.0'></center>''')
+
+    # with gr.Tab("Whisper Transcribe Japanese Audio"):
+    #     gr.Markdown(f'''
+    #           <div>
+    #           <h1 style='text-align: center'>Whisper Transcribe Japanese Audio</h1>
+    #           </div>
+    #           Transcribe long-form microphone or audio inputs with the click of a button! The fine-tuned
+    #           checkpoint <a href='https://huggingface.co/{MODEL_NAME}' target='_blank'><b>{MODEL_NAME}</b></a> to transcribe audio files of arbitrary length.
+    #       ''')
+    #     microphone = gr.inputs.Audio(source="microphone", type="filepath", optional=True)
+    #     upload = gr.inputs.Audio(source="upload", type="filepath", optional=True)
+    #     transcribe_btn = gr.Button("Transcribe Audio")
+    #     text_output = gr.Textbox()
+    #     with gr.Row():
+    #         gr.Markdown('''
+    #             ### You can test by following examples:
+    #             ''')
+    #     examples = gr.Examples(examples=
+    #                            ["sample1.wav",
+    #                             "sample2.wav",
+    #                             ],
+    #                            label="Examples", inputs=[upload])
+    #     transcribe_btn.click(transcribe, [microphone, upload], outputs=text_output)
+    #
+    # with gr.Tab("Whisper Transcribe Japanese YouTube"):
+    #     gr.Markdown(f'''
+    #           <div>
+    #           <h1 style='text-align: center'>Whisper Transcribe Japanese YouTube</h1>
+    #           </div>
+    #             Transcribe long-form YouTube videos with the click of a button! The fine-tuned checkpoint:
+    #             <a href='https://huggingface.co/{MODEL_NAME}' target='_blank'><b>{MODEL_NAME}</b></a> to transcribe audio files of arbitrary length.
+    #         ''')
+    #     youtube_link = gr.Textbox(label="Youtube url", lines=1, interactive=True)
+    #     yt_transcribe_btn = gr.Button("Transcribe YouTube")
+    #     text_output2 = gr.Textbox()
+    #     html_output = gr.Markdown()
+    #     yt_transcribe_btn.click(yt_transcribe, [youtube_link], outputs=[html_output, text_output2])
+
+demo.launch(debug=True)