speech2video.py

# -*- coding: utf-8 -*-
"""Speech2Video.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1CcYNY0wwS05Ml7UVv4oY7cHjlVrhTbIq
"""

from google.colab import drive
drive.mount('/content/drive')

!apt-get install python3-pyaudio
!pip install SpeechRecognition
!pip install pydub

from pydub import AudioSegment
import speech_recognition as sr
import re
import nltk
from nltk.stem import PorterStemmer, WordNetLemmatizer
from nltk.tokenize import word_tokenize

nltk.download('punkt')
nltk.download('wordnet')

!pip install modelscope==1.4.2
!pip install open_clip_torch
!pip install pytorch-lightning

from modelscope.pipelines import pipeline
from modelscope.outputs import OutputKeys

p = pipeline('text-to-video-synthesis', 'damo/text-to-video-synthesis')

def convert_to_wav(input_file, output_file):
    audio = AudioSegment.from_ogg(input_file)
    audio.export(output_file, format="wav")

# Function to convert audio file to text
def speech_to_text(audio_file):
    recognizer = sr.Recognizer()
    with sr.AudioFile(audio_file) as source:
        audio = recognizer.record(source)
        try:
            text = recognizer.recognize_google(audio)
            return text
        except sr.UnknownValueError:
            print("Sorry, could not understand audio")
            return ""
        except sr.RequestError as e:
            print("Error fetching results; {0}".format(e))
            return ""

# Function to preprocess text
def preprocess_text(text):
    # Remove non-alphabetic characters
    text = re.sub(r'[^a-zA-Z\s]', '', text)

    # Tokenize the text
    tokens = word_tokenize(text)

    porter_stemmer = PorterStemmer()
    lemmatizer = WordNetLemmatizer()

    stemmed_tokens = [porter_stemmer.stem(token) for token in tokens]
    lemmatized_tokens = [lemmatizer.lemmatize(token) for token in tokens]

    lemmatized_text = ' '.join(lemmatized_tokens)

    return lemmatized_text

# Main function
def main():
    # Input and output file paths
    input_file = "/content/drive/MyDrive/IV II PROJECT/WhatsApp Audio 2024-03-24 at 8.52.04 AM.ogg"
    output_file = "/content/drive/MyDrive/IV II PROJECT/converted_audio.wav"

    # Convert .ogg to .wav
    convert_to_wav(input_file, output_file)

    # Convert audio to text
    text = speech_to_text(output_file)
    print("Text from audio:", text)

    # Preprocess text
    preprocessed_text = preprocess_text(text)
    print("Preprocessed text:", preprocessed_text)

    test_text = {
        'text': preprocessed_text,
    }
    output_video_path = p(test_text,)[OutputKeys.OUTPUT_VIDEO]
    print('output_video_path:', output_video_path)
    from google.colab import files
    files.download(output_video_path)

if __name__ == "__main__":
    main()