awfultranslator.py

import os
import tortoise
from tortoise import api
import requests
import speech_recognition as sr
from googletrans import Translator
from pydub import AudioSegment
from pydub.playback import play

def convert_ogg_to_wav(ogg_file, wav_file):
    audio = AudioSegment.from_ogg(ogg_file)
    audio.export(wav_file, format="wav")

def recognize_audio(audio_file, target_language='pt'):
    wav_file = "temp.wav"
    convert_ogg_to_wav(audio_file, wav_file)

    # Load the converted WAV file
    with sr.AudioFile(wav_file) as source:
        audio_data = sr.Recognizer().record(source)

    # Recognize (convert from speech to text)
    try:
        text = sr.Recognizer().recognize_google(audio_data, language='en')  # Change 'en' to the appropriate language code
        return text
    except sr.UnknownValueError:
        return None

def translate_text(text):
    translator = Translator()
    try:
        translated_text = translator.translate(text, dest='pt')
        return translated_text.text
    except Exception as e:
        print(f"Error during translation: {e}")
        translated_text = "Failed To Translate"

def generate_audio(translated_text, output_file='output.wav', lang='pt'):
    text = translated_text
    tts = api.TextToSpeech(kv_cache=True, half=True)
    pcm_audio = tts.tts_with_preset(text, voice="tom", preset='fast')
    pcm_audio.export(output_file, format='ogg', codec='libvorbis')



def process_audio_folder(folder_path):
    for root, _, files in os.walk(folder_path):
        for filename in files:
            if filename.lower().endswith('.ogg'):
                audio_file_path = os.path.join(root, filename)
                translated_audio_path = os.path.join(root, f"{os.path.splitext(filename)[0]}.ogg")

                # Step 1: Speech to Text
                recognized_text = recognize_audio(audio_file_path)
                if recognized_text:
                    print(f"Recognized text from {audio_file_path}: {recognized_text}")

                    # Step 2: Translation
                    translated_text = translate_text(recognized_text)
                    print(f"Translated text: {translated_text}")

                    # Step 3: Text to Speech
                    generate_audio(translated_text, output_file=translated_audio_path)
                    print(f"Translated audio saved to {translated_audio_path}")
                else:
                    print(f"Could not understand audio from {audio_file_path}")

# Example usage:
if __name__ == "__main__":
    audio_folder_path = '/home/davi/Documents/The Jackbox Party Pack 7/games/Quiplash3/content/Quiplash3Round1Question/'
    process_audio_folder(audio_folder_path)