app.py

# Import the required libraries
import streamlit as st
import whisper
import speech_recognition as sr
from pydub import AudioSegment
import os

# Function to transcribe audio using OpenAI Whisper
def transcribe_whisper(model_name, file_path):
    model = whisper.load_model(model_name)
    result = model.transcribe(file_path)
    return result["text"]

# Function to transcribe audio using Google Speech API
def transcribe_speech_recognition(file_path):
    r = sr.Recognizer()
    with sr.AudioFile(file_path) as source:
        r.adjust_for_ambient_noise(source)
        audio = r.record(source)
    result = r.recognize_google(audio)
    return result

# Function to convert mp3 file to wav
def convert_mp3_to_wav(mp3_path):
    audio = AudioSegment.from_mp3(mp3_path)
    wav_path = mp3_path.replace('.mp3', '.wav')
    audio.export(wav_path, format="wav")
    return wav_path

def main():
    st.title('Transcriptor de Audio')

    uploaded_file = st.file_uploader("Sube tu archivo de audio para transcribir", type=['wav', 'mp3'])

    if uploaded_file is not None:
        file_details = {"FileName":uploaded_file.name, "FileType":uploaded_file.type, "FileSize":uploaded_file.size}
        st.write(file_details)

        # Save uploaded file to temp directory
        file_path = os.path.join("temp", uploaded_file.name)
        with open(file_path, "wb") as f:
            f.write(uploaded_file.getbuffer())
        
        st.write("Archivo de audio cargado correctamente. Por favor, selecciona el método de transcripción.")
        transcription_method = st.selectbox('Escoge el método de transcripción', ('OpenAI Whisper', 'Google Speech API'))

        if transcription_method == 'OpenAI Whisper':
            model_name = st.selectbox('Escoge el modelo de Whisper', ('base', 'small', 'medium', 'large', 'tiny'))
        elif transcription_method == 'Google Speech API' and file_path.endswith('.mp3'):
            # Convert mp3 to wav if Google Speech API is selected and file is in mp3 format
            file_path = convert_mp3_to_wav(file_path)

        if st.button('Transcribir'):
            with st.spinner('Transcribiendo...'):
                if transcription_method == 'OpenAI Whisper':
                    transcript = transcribe_whisper(model_name, file_path)
                else:
                    transcript = transcribe_speech_recognition(file_path)

            st.text_area('Resultado de la Transcripción:', transcript, height=200)

if __name__ == "__main__":
    main()