This commit is contained in:
oobabooga 2023-07-12 11:33:25 -07:00
parent 9b55d3a9f9
commit e202190c4f
24 changed files with 146 additions and 125 deletions

View file

@ -16,7 +16,7 @@ params = {
}
def do_stt(audio,whipser_model,whipser_language):
def do_stt(audio, whipser_model, whipser_language):
transcription = ""
r = sr.Recognizer()
@ -33,10 +33,10 @@ def do_stt(audio,whipser_model,whipser_language):
return transcription
def auto_transcribe(audio, auto_submit,whipser_model,whipser_language):
def auto_transcribe(audio, auto_submit, whipser_model, whipser_language):
if audio is None:
return "", ""
transcription = do_stt(audio,whipser_model,whipser_language)
transcription = do_stt(audio, whipser_model, whipser_language)
if auto_submit:
input_hijack.update({"state": True, "value": [transcription, transcription]})
@ -50,11 +50,11 @@ def ui():
with gr.Row():
with gr.Accordion("Settings", open=False):
auto_submit = gr.Checkbox(label='Submit the transcribed audio automatically', value=params['auto_submit'])
whipser_model = gr.Dropdown(label='Whisper Model', value=params['whipser_model'],choices=["tiny.en","base.en", "small.en","medium.en","tiny","base","small","medium","large"])
whipser_language = gr.Dropdown(label='Whisper Language', value=params['whipser_language'],choices=["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"])
whipser_model = gr.Dropdown(label='Whisper Model', value=params['whipser_model'], choices=["tiny.en", "base.en", "small.en", "medium.en", "tiny", "base", "small", "medium", "large"])
whipser_language = gr.Dropdown(label='Whisper Language', value=params['whipser_language'], choices=["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"])
audio.change(
auto_transcribe, [audio, auto_submit,whipser_model,whipser_language], [shared.gradio['textbox'], audio]).then(
auto_transcribe, [audio, auto_submit, whipser_model, whipser_language], [shared.gradio['textbox'], audio]).then(
None, auto_submit, None, _js="(check) => {if (check) { document.getElementById('Generate').click() }}")
whipser_model.change(lambda x: params.update({"whipser_model": x}), whipser_model, None)
whipser_language.change(lambda x: params.update({"whipser_language": x}), whipser_language, None)