| import gradio as gr | |
| import whisper | |
| # Load the Whisper model (you can change to "base", "small", "medium", etc.) | |
| model = whisper.load_model("base") | |
| # Function to process the audio file and transcribe | |
| def transcribe_audio(audio): | |
| # Transcribe the audio using Whisper | |
| result = model.transcribe(audio) | |
| return result['text'] | |
| # Create a Gradio interface for audio transcription | |
| iface = gr.Interface( | |
| fn=transcribe_audio, # The function that will process the audio | |
| inputs=gr.Audio(source="upload", type="filepath"), # Upload audio input | |
| outputs="text", # Output transcription as text | |
| title="Whisper Audio Transcription", # Title of the interface | |
| description="Upload an audio file and get the transcription using OpenAI's Whisper model." # Description | |
| ) | |
| # Launch the interface | |
| iface.launch() | |