INNER CODE UNIT · Python

transcribe_youtube

sanchit-gandhi/whisper-jax · app/app.py:190

    def transcribe_youtube(yt_url, task, return_timestamps, progress=gr.Progress()):
        progress(0, desc="Loading audio file...")
        logger.info("loading youtube file...")
        html_embed_str = _return_yt_html_embed(yt_url)
        with tempfile.TemporaryDirectory() as tmpdirname:
            filepath = os.path.join(tmpdirname, "video.mp4")
            download_yt_audio(yt_url, filepath)

            with open(filepath, "rb") as f:
                inputs = f.read()

        inputs = ffmpeg_read(inputs, pipeline.feature_extractor.sampling_rate)
        inputs = {"array": inputs, "sampling_rate": pipeline.feature_extractor.sampling_rate}
        logger.info("done loading...")
        text, runtime = tqdm_generate(inputs, task=task, return_timestamps=return_timestamps, progress=progress)
        return html_embed_str, text, runtime

    microphone_chunked = gr.Interface(

View source record →