Spaces:
Running
Running
| import os | |
| os.system("pip install git+https://github.com/openai/whisper.git") | |
| import gradio as gr | |
| import whisper | |
| model = whisper.load_model("large") | |
| import time | |
| def transcribe(audio): | |
| # split the audio for 30 seconds | |
| audio = whisper.load_audio(audio) | |
| audio = whisper.pad_or_trim(audio) | |
| # make log-Mel spectrogram and move to device as the model | |
| mel = whisper.log_mel_spectrogram(audio).to(model.device) | |
| # detect the spoken language | |
| _, probs = model.detect_language(mel) | |
| print(f"Detected language: {max(probs, key=probs.get)}") | |
| # decoding the audio | |
| options = whisper.DecodingOptions(fp16 = False) | |
| result = whisper.decode(model, mel, options) | |
| print(result.text) | |
| return result.text | |
| gr.Interface( | |
| title = 'Speech to Text with OpenAI (large)', | |
| fn=transcribe, | |
| inputs=[ | |
| gr.inputs.Audio(source="microphone", type="filepath") | |
| ], | |
| outputs=[ | |
| "textbox" | |
| ], | |
| live=True).launch() | |