app.py

import gradio as gr
from transformers import pipeline

# Load the Hugging Face ASR model
asr_pipeline = pipeline("automatic-speech-recognition", model="openai/whisper-base")

def transcribe(audio):
    """Convert speech to text using Hugging Face ASR model."""
    result = asr_pipeline(audio)
    return result["text"]

# Gradio Interface
demo = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(type="filepath"),  # Remove 'source' argument
    outputs=gr.Textbox(label="Transcription"),
    title="Speech to Text with Hugging Face ASR",
    description="Click the button and speak. Your voice will be transcribed using OpenAI Whisper.",
    live=True  # Enables real-time transcription
)

demo.launch()