app.py

import gradio as gr
from transformers import pipeline

# Load Whisper pipeline
pipe = pipeline(task="automatic-speech-recognition", model="openai/whisper-small")

# Function to transcribe audio file
def transcribe(audio_file):
    if audio_file is None:
        return "Please upload an audio file."
    return pipe(audio_file)["text"]

# Gradio Interface
with gr.Blocks() as app:
    gr.Markdown("## 🎙️ Whisper Speech-to-Text (ASR)\nUpload or record audio and get transcription.")
    
    with gr.Row():
        audio_input = gr.Audio(type="filepath", label="Upload or Record Audio")
        output_text = gr.Textbox(label="Transcription")
    
    transcribe_btn = gr.Button("Transcribe")
    transcribe_btn.click(fn=transcribe, inputs=audio_input, outputs=output_text)


app.launch()