app.py

import gradio as gr
import whisper

# Load the Whisper model
model = whisper.load_model("base")

def transcribe(audio_file):
    # Process the audio file directly with the file path
    result = model.transcribe(audio_file)

    # Return the transcription
    return result['text']

# Create the Gradio interface
iface = gr.Interface(fn=transcribe,
                     inputs=gr.inputs.Audio(sources="upload", type="file", label="Upload Audio"),
                     outputs="text",
                     title="Whisper Transcription",
                     description="Upload an audio file to transcribe it using OpenAI's Whisper model.")

# Launch the app
if __name__ == "__main__":
    iface.launch()