app.py

import gradio as gr
from transformers import pipeline

# Load the Whisper model for Hindi transcription
pipe = pipeline(model="Tashuu/whisper-medium-hindi")

def transcribe_audio(audio):
    """
    Transcribes the uploaded audio file using the fine-tuned Whisper model.
    """
    try:
        transcription = pipe(audio)["text"]
        return transcription
    except Exception as e:
        return f"Error during transcription: {str(e)}"

# Define the Gradio interface
interface = gr.Interface(
    fn=transcribe_audio,
    inputs=gr.Audio(type="filepath"),
    outputs="text",
    title="Hindi Speech-to-Text Transcription",
    description="Upload an audio file in Hindi, and this app will transcribe it to text using a fine-tuned Whisper model."
)

# Launch the app
interface.launch()