Spaces:
Runtime error
Runtime error
| import whisper | |
| model = whisper.load_model("medium") | |
| from transformers import pipeline | |
| en_fr_translator = pipeline("translation_en_to_fr") | |
| import gradio as gr | |
| import time | |
| 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", | |
| "iw": "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", | |
| } | |
| def transcribe(audio): | |
| # load audio and pad or trim it to fit 30 seconds | |
| audio = whisper.load_audio(audio) | |
| audio = whisper.pad_or_trim(audio) | |
| # make log-Mel spectrogram and move to the same device as the model | |
| mel = whisper.log_mel_spectrogram(audio).to(model.device) | |
| # detect the spoken language | |
| _, probs = model.detect_language(mel) | |
| language= max(probs, key=probs.get) | |
| lang = LANGUAGES[language] | |
| #lang=(f"Detected language: {max(probs, key=probs.get)}") | |
| lang=(f"Detected language: {lang}") | |
| # decode the audio | |
| options = whisper.DecodingOptions(fp16 = False,task= "translate") | |
| result = whisper.decode(model, mel, options) | |
| word= result.text | |
| trans = en_fr_translator(word) | |
| Trans = trans[0]['translation_text'] | |
| result=f"{lang}\n{word}\n\nFrench translation: {Trans}" | |
| return result | |
| gr.Interface( | |
| title = 'OpenAI Whisper ASR Gradio Web UI',description="This app will take an audio input and it will try to guess the language and also translate it to french ", | |
| fn=transcribe, | |
| inputs=[ | |
| gr.inputs.Audio(source="microphone", type="filepath") | |
| ], | |
| outputs=[ | |
| "textbox" | |
| ], | |
| live=True).launch() |