app.py

import streamlit as st
import logging
from transformers import pipeline

# Setup logging
logging.basicConfig(level=logging.INFO)

# Load speech recognition pipeline
asr = pipeline(task="automatic-speech-recognition",
               model="facebook/wav2vec2-base-960h")

# Function for transcribing speech
def transcribe_speech(audio_file):
    if not audio_file:
        logging.error("No audio file provided.")
        return "No audio found, please retry."
    try:
        logging.info(f"Processing file: {audio_file.name}")
        audio_input = audio_file.read()
        output = asr(audio_input)
        return output[0]['transcription']
    except Exception as e:
        logging.error(f"Error during transcription: {str(e)}")
        return f"Error processing the audio file: {str(e)}"

# Streamlit app UI
def main():
    st.title("Simple Speech Recognition App")
    st.write("### This app allows you to record or upload audio and see its transcription.")
    
    # Upload audio file or record from microphone
    audio_file = st.file_uploader("Upload Audio File", type=["wav", "mp3"])
    if audio_file:
        st.audio(audio_file, format='audio/wav')

    # Button to transcribe audio
    if st.button("Transcribe Audio"):
        if audio_file:
            transcription = transcribe_speech(audio_file)
            st.write("### Transcription:")
            st.write(transcription)
        else:
            st.warning("Please upload an audio file first.")

if __name__ == "__main__":
    main()