| import whisper | |
| import gradio as gr | |
| import datetime | |
| model = whisper.load_model('base') | |
| def transcribe(inputs , timestamp): | |
| if inputs is None: | |
| raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.") | |
| output = "" | |
| result = model.transcribe(inputs) | |
| if timestamp == "Yes": | |
| for indx, segment in enumerate(result['segments']): | |
| output += str(datetime.timedelta (seconds=segment['start'])) +" "+ str(datetime.timedelta (seconds=segment['end'])) + "\n" | |
| output += segment['text'].strip() + '\n' | |
| else: | |
| output = result["text"] | |
| return output | |
| interface = gr.Interface( | |
| fn=transcribe, | |
| inputs=[gr.Audio(sources=["upload"],type="filepath"), | |
| gr.Radio(["Yes", "No"], label="Timestamp", info="Displays with timestamp if needed."),], | |
| outputs="text", | |
| title="Whisper Large V3: Transcribe Audio", | |
| description=( | |
| "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the OpenAI Whisper API" | |
| ) | |
| ) | |
| interface.launch() |