main.py

import whisper
import yt_dlp
import gradio as gr

def yt_download(link):
    if not link.strip():
        gr.Info("You need to provide a download link.")
        print("You need to provide a download link")
        return None
    ydl_opts = {
        'format': 'bestaudio',
        'outtmpl': '%(title)s',
        'nocheckcertificate': True,
        'ignoreerrors': True,
        'no_warnings': True,
        'quiet': True,
        'extractaudio': True,
        'postprocessors': [{'key': 'FFmpegExtractAudio', 'preferredcodec': 'wav'}],
        'postprocessor_args': [
            '-acodec', 'pcm_f32le'
        ],
    }
    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
        result = ydl.extract_info(link, download=True)
        download_path = ydl.prepare_filename(result, outtmpl='%(title)s.wav')
        
    return download_path


def whisper_(input_audio):
    model = whisper.load_model("medium")
    
    # load audio and pad/trim it to fit 30 seconds
    audio = whisper.load_audio(input_audio)
    audio = whisper.pad_or_trim(audio)
    # make log-Mel spectrogram and move to the same device as the model
    mel = whisper.log_mel_spectrogram(audio, n_mels=model.dims.n_mels).to(model.device)
    
    # detect the spoken language
    _, probs = model.detect_language(mel)
    print(f"Detected language: {max(probs, key=probs.get)}")
    
    # decode the audio
    options = whisper.DecodingOptions()
    result = whisper.decode(model, mel, options)
    # print the recognized text
    
    text_result = result.text
    return text_result