Building a song transcription system with profanity filter usi..

Overview and prerequisites

Building the song transcription system with profanity filter

What is a profanity filter?

Step 1: Separate vocals from instrumentals using Spleeter

1. Extracting the vocals using Spleeter

import os
import requests
import warnings
from openai import OpenAI
from spleeter.separator import Separator

def extract_vocals(path_to_file: str, path_to_output: str) -> str:
    os.environ['CUDA_VISIBLE_DEVICES']=' ' # comment out
    separator = Separator(params_descriptor='spleeter:4stems-16kHz', multiprocess=False)

def extract_vocals(path_to_file: str, path_to_output: str) -> str:
    os.environ['CUDA_VISIBLE_DEVICES']=' '
    separator = Separator(params_descriptor='spleeter:4stems-16kHz', multiprocess=False)
    separator.separate_to_file(path_to_file, path_to_output)

2. Selecting the vocals file

def extract_vocals(path_to_file: str, path_to_output: str) -> str:
    os.environ['CUDA_VISIBLE_DEVICES']=' '
    separator = Separator(params_descriptor='spleeter:4stems-16kHz', multiprocess=False)
    separator.separate_to_file(path_to_file, path_to_output)
    filename = path_to_file.split('/')[-1].split('.')[0]
   
    # combine output filepath and filename
    wav_path = os.path.join(path_to_output, filename)
   
    # Removes all other splits and leaves only the vocals in the directory
    for i in os.listdir(wav_path):
        if i!='vocals.wav':
            os.remove(os.path.join(wav_path, i))
            # Returns the music filename
    return filename

Step 2: Transcribe the vocals using Gladia Whisper API

def get_lyrics(filename: str, audio_file):
   
    headers = {
        'Content-Type': 'application/json',
        'x-gladia-key': f'{gladia_key}'
    }

def get_lyrics(filename: str, audio_file):
   
    filename = filename
   
    headers = {
        'accept': 'application/json',
        'x-gladia-key': f'{gladia_key}'
    }
   
    with open(audio_file, 'rb') as f:
        _, ext = os.path.splitext(audio_file)
        files = {
            'audio': (filename, f, f'audio/{ext[1:]}'),
            'toggle_noise_reduction': 'true'
            }


        # Pass the headers and files and send as a request
        response = requests.post('https://api.gladia.io/audio/text/audio-transcription/',
                                headers=headers,
                                files=files)
       
        # convert response to json
        response = response.json()
       
        # Retrieve each transcripted sentence defined by a full stop from the resulting dictionary
        sentences = [item["transcription"] for item in response["prediction"]]
   
        # Extract them from a list and join them together to form a full sentence
        transcript = " ".join(sentences)
       
    return transcript

Step 3: Prompt engineering GPT 3.5 as a profanity filter

def determine_safety(lyrics):
   
    prompt = f"""
   
    You will be provided with the lyrics of a song that has been transcribed from the original audio file. There is a possibility that the transcription might not be entirely complete.
    Your duty is to study with intent the overall context of the song and the words used and look out for anything that promotes or denotes violence, sex, drugs, alcohol. After your analysis,
    you are to determine if the song is safe for a group of people who don't like profanites to listen to. You are not to generate any text in excess. If the song contains profanities whether explicit or implicit, your response should be 'Profanities detected, song promotes [write what the song promotes here]',
    otherwise your response should be 'No profanities detected, safe to listen to'.
   
    Note that the only criteria that should be used to determine the safety is the explicit or implicit mention of drugs, violence, sex and alcohol.
    Make sure to go over the context of the lyrics for subtle hints at any of the profanities (drugs, violence, sex and violence) and only give a response when you're sure of your answer.
   
    Make sure that your only responses are 'Profanities detected, song promotes [write what the song promotes here]' and 'No profanities detected, safe to listen to'.
   
    THESE ARE THE LYRICS\n
    {lyrics}.
   
    """
   
    response = client.chat.completions.create(
        model='gpt-3.5-turbo-0125',
        messages=[
            {"role": "system",
             "content": prompt}
            ],
        temperature = 0.25,
   
        )
   
    return response.choices[0].message

Step 4: Creation of a pipeline to automate the workflow

def run():
    # define the file paths
    path_to_file =  "C:/path/other path/song.mp3"
    output = "C:/path/other path/output_file_name"


    # Function to extract the vocals using Spleeter
    vocal_filename = extract_vocals(path_to_file, output)


    # the path to the newly created folder for the separated music files
    new_audio_path = os.path.join(output, vocal_filename)


    # the path to the newly created vocals.wav file
    audio_file_in_path = os.path.join(new_audio_path, os.listdir(new_audio_path)[0])


    # Function to transcribe the vocals using Gladia Whisper API
    transcription = get_lyrics(filename = vocal_filename,
                            audio_file = audio_file_in_path)


    print(f'THE TRANSCRIPTION \n{transcription}')


    # Function to use GPT 3.5 as a profanity filter
    safe_value = determine_safety(transcription)
    print(safe_value)
   
run()

Conclusion

About Gladia