Skip to main content

OpenAI Learning:- Chapter 5

 Generative AI-Powered Audio/Video Processing: Whisper's Python Adventure

What Is the Purpose of This Application?
An application that displays the ability of Generative AI to process and analyze audio/video files, and then output the lyrics for that audio or video file.

Sample code:

import streamlit as st
from pytube import YouTube
import os
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline

def get_mp3(url):
    yt = YouTube(str(url))
    audio = yt.streams.filter(only_audio = True).first()
    destination = '.'
    out_file = audio.download(output_path=destination)
    base, ext = os.path.splitext(out_file)
    new_file = base + '.mp3'
    os.rename(out_file, new_file)
    return new_file

def get_transcript(audio_file):
    device = "cuda:0" if torch.cuda.is_available() else "cpu"  #If you have GPU else it will use cpu
    torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
    model_id = "openai/whisper-tiny"    # define the model
    model = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True)
    model.to(device)
    processor = AutoProcessor.from_pretrained(model_id)
   
    # create the pipeline
    pipe = pipeline(
        "automatic-speech-recognition",
        model=model,
        tokenizer=processor.tokenizer,
        feature_extractor=processor.feature_extractor,
        max_new_tokens=128,
        chunk_length_s=30,
        batch_size=16,
        return_timestamps=True,
        torch_dtype=torch_dtype,
        device=device,
        generate_kwargs={"language": "english"})
   
    result = pipe(audio_file, return_timestamps=True,generate_kwargs={"language": "english"})
    result = result["chunks"]
    return result

def format_lyrics(lyrics):
    formatted_lyrics = ""
    for line in lyrics:
        text = line["text"]
        formatted_lyrics += f"{text}\n\n"
    return formatted_lyrics.strip()

def fetch_lyrics(url):
    mp3 = get_mp3(url)
    status_placeholder = st.empty()
    status_placeholder.subheader("Please wait for few seconds. Preparing the lyrics for you...")
    lyrics = get_transcript(mp3)
    status_placeholder.empty()
    lyrics = format_lyrics(lyrics)
    return lyrics

def main():
    text_color = "#7dd100"
    #st.markdown('<p style="color: #006fd1; font-family: sans-serif; text-align:center; font-size: 65px;"><b>YouTube Lyrics App</b></p>', unsafe_allow_html=True)
    st.markdown("""<p style="color: #d15000;font-size: 70px;font-family: sans-serif; text-align:center;margin-bottom:0px;"><b>Lyrics</b><span style="color: #E94B3CFF;font-size: 70px;font-family: sans-serif;"><b>Box</b></span></p>""", unsafe_allow_html=True)
    st.markdown('<p style="font-family: sans-serif; text-align:center; font-size: 20px; margin-bottom:60px;">Get the Lyrics of your Favorite Song for Free</p>', unsafe_allow_html=True)
    # Input field for the user to enter the URL of the song
    st.markdown('<p style="font-family: sans-serif; text-align:left; font-size: 20px; margin-bottom:0px;">Enter the audio/video link below:</p>', unsafe_allow_html=True)
    url = st.text_input("", "")

    if url:
        # Button to trigger fetching and displaying the lyrics
        if st.button("Get Lyrics of this A/V"):
            lyrics = fetch_lyrics(url)
            st.subheader("Lyrics:")
            st.write(lyrics)

    st.markdown('<p style="font-size: 35px;font-family: sans-serif; text-align:left; margin-top: 100px;"><b>How to Get the Lyrics of your Video?</b></p>', unsafe_allow_html=True)
    st.markdown('<p style="font-family: sans-serif; text-align:left; font-size: 20px">To extract the lyrics of your favorite video using this tool follow the steps. <br /> <br /> &ensp; 1. Copy the link of the video from Youtube. \
                <br /> &ensp; 2. Paste the link in the box above. <br /> &ensp; 3. Hit the "Get Lyrics of this A/V" button. </p>', unsafe_allow_html=True)
   
    st.markdown('<p style="font-size: 35px;font-family: sans-serif; text-align:left; margin-top: 40px;"><b>Why Should you use this tool?</b></p>', unsafe_allow_html=True)
    st.markdown('<p style="font-family: sans-serif; text-align:left; font-size: 20px">Features of this tool are given below: <br /> <br /> \
                &ensp; 1. This Tool uses <a href="https://huggingface.co/openai/whisper-tiny/">OpenAI Whisper</a> to extract transcript from audio file.\
                <br /> &ensp; 2. We do not save your data or video.\
                <br /> &ensp; 3. Easy and Free-to-use.</p>', unsafe_allow_html=True)

if __name__ == "__main__":
    main()
Labels:

Comments

Post a Comment

Popular posts from this blog

How to Unzip files in Selenium (Java)?

1) Using Java (Lengthy way) : Create a utility and use it:>> import java.io.BufferedOutputStream; import org.openqa.selenium.io.Zip; import java.io.File; import java.io.FileInputStream; import java.io.FileOutputStream; import java.io.IOException; import java.util.zip.ZipEntry; import java.util.zip.ZipInputStream;   public class UnzipUtil {     private static final int BUFFER_SIZE = 4096;     public void unzip (String zipFilePath, String destDirectory) throws IOException {         File destDir = new File(destDirectory);         if (!destDir.exists()) {             destDir.mkdir();         }         ZipInputStream zipIn = new ZipInputStream(new FileInputStream(zipFilePath));         ZipEntry entry = zipIn.getNextEntry();         // to iterates over entries in the zip folder         while (entry != null) {             String filePath = destDirectory + File.separator + entry.getName();             if (!entry.isDirectory()) {                 extractFile (zipIn, filePath);            
Post a Comment
Read more

Encode/Decode the variable/response using Postman itself

We get a lot of use cases where we may have to implement Base64 encoding and/or decoding while building our APIs. And, if you are wondering if it is possible to encode/decode the variable/response using Postman itself or how to encode/decode the token or password in postman and save it in a variable? To Base64 encode/decode, the quickest way is to use JavaScript methods btoa, atob: atob - It turns base64-encoded ASCII data back to binary. btoa - It turns binary data to base64-encoded ASCII. Sample code : var responseBody = pm.response.json(); var parsedPwd = JSON.parse(atob(responseBody.password)); // presuming password is in the payload pm.collectionVariables.set("password", parsedPwd);
Post a Comment
Read more

The use of Verbose attribute in testNG or POM.xml (maven-surefire-plugin)

At times, we see some weird behavior in your testNG execution and feel that the information displayed is insufficient and would like to see more details. At other times, the output on the console is too verbose and we may want to only see the errors. This is where a verbose attribute can help you- it is used to define the amount of logging to be performed on the console. The verbosity level is 0 to 10, where 10 is most detailed. Once you set it to 10, you'll see that console output will contain information regarding the tests, methods, and listeners, etc. <suite name="Suite" thread-count="5" verbose="10"> Note* You can specify -1 and this will put TestNG in debug mode. The default level is 0. Alternatively, you can set the verbose level through attribute in "maven-surefire-plugin" in pom.xml, as shown in the image. #testNG #automationTesting #verbose # #testAutomation
Post a Comment
Read more