app.py

import gradio as gr
import torch
import whisper

# Load the Whisper model
model = whisper.load_model("large-v3")

def transcribe(audio):
    """Transcribes the given audio file."""
    audio_path = audio if isinstance(audio, str) else audio.name
    result = model.transcribe(audio_path)
    return result["text"]

with gr.Blocks(fill_height=True) as demo:
    with gr.Sidebar():
        gr.Markdown("# Audio Transcription")
        gr.Markdown("This demo uses the OpenAI Whisper-large-v3 model for audio transcription.")
    
    gr.Markdown("### Upload an audio file to transcribe")
    audio_input = gr.Audio(source="upload", type="filepath")
    output_text = gr.Textbox(label="Transcription")
    transcribe_button = gr.Button("Transcribe")
    
    transcribe_button.click(fn=transcribe, inputs=audio_input, outputs=output_text)

demo.launch()