import numpy as np
import streamlit as st
import speech_recognition as sr
import os
import tempfile
import librosa
import soundfile as sf

def convert_to_wav(audio_file):
    y, sr = librosa.load(audio_file, sr=None)
    with tempfile.NamedTemporaryFile(delete=False, suffix='.wav') as tmp_wav:
        sf.write(tmp_wav.name, y, sr, format='wav')
        return tmp_wav.name

def transcribe_audio(audio_file):
    recognizer = sr.Recognizer()
    with sr.AudioFile(audio_file) as source:
        audio = recognizer.record(source)
    try:
        return recognizer.recognize_google(audio)
    except sr.UnknownValueError:
        return "Speech recognition could not understand the audio"
    except sr.RequestError as e:
        return f"Could not request results from speech recognition service; {e}"

def main():
    st.title("Speech-to-Text Converter")
    uploaded_file = st.file_uploader("Choose an audio file", type=["wav", "mp3", "m4a", "ogg", "flac"])
    
    if uploaded_file is not None:
        st.audio(uploaded_file)
        if st.button("Transcribe"):
            with tempfile.NamedTemporaryFile(delete=False, suffix='.' + uploaded_file.name.split('.')[-1]) as tmp_file:
                tmp_file.write(uploaded_file.getvalue())
                tmp_file_path = tmp_file.name
            
            try:
                wav_file_path = convert_to_wav(tmp_file_path)
                transcription = transcribe_audio(wav_file_path)
                st.write("Transcription:")
                st.write(transcription)
            except Exception as e:
                st.error(f"An error occurred: {str(e)}")
            finally:
                os.unlink(tmp_file_path)
                if 'wav_file_path' in locals():
                    os.unlink(wav_file_path)

if __name__ == "__main__":
    main()