# Import the required libraries
import streamlit as st
import whisper
import speech_recognition as sr
from pydub import AudioSegment
import os
import sounddevice as sd
import numpy as np
from scipy.io.wavfile import write
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, duration=0.5)  # Adjust ambient noise threshold
        audio = r.record(source)

    try:
        result = r.recognize_google(audio, language='es')
        return result
    except sr.UnknownValueError:
        return "No se pudo reconocer ningún texto en el audio."

# 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

# Function to record audio
def record_audio(filename, duration):
    fs = 44100  # Sample rate
    channels = 2  # Number of channels (1 for mono, 2 for stereo)
    
    # Start recording
    recording = sd.rec(int(duration * fs), samplerate=fs, channels=channels)
    sd.wait()  # Wait until recording is finished
    # Create temp directory if it doesn't exist
    if not os.path.exists(os.path.dirname(filename)):
        os.makedirs(os.path.dirname(filename))

    # Save as WAV file
    write(filename, fs, recording)

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

    # Choose the transcription method and model
    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'))

    option = st.selectbox('Escoge la opción', ('Subir un archivo', 'Grabar audio en tiempo real'))

    if option == 'Subir un archivo':
        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. Transcribiendo...")
            with st.spinner('Transcribiendo...'):
                if uploaded_file.name.endswith('.mp3') and transcription_method != 'OpenAI Whisper':
                    # Convert mp3 to wav if Google Speech API is selected and file is in mp3 format
                    file_path = convert_mp3_to_wav(file_path)

                # Perform transcription
                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)
    
    elif option == 'Grabar audio en tiempo real':
        duration = st.slider("Selecciona la duración de la grabación (segundos)", 1, 10, 5)
        start_recording = st.button('Empezar a grabar')

        if start_recording:
            filename = "temp/recorded_audio.wav"
            st.write("Grabación en progreso...")
            with st.spinner('Grabando...'):
                record_audio(filename, duration)
            
            st.write("Grabación finalizada. Transcribiendo...")
            with st.spinner('Transcribiendo...'):
                # Perform transcription
                if transcription_method == 'OpenAI Whisper':
                    transcript = transcribe_whisper(model_name, filename)
                else:
                    transcript = transcribe_speech_recognition(filename)

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

if __name__ == "__main__":
    main()