Kadir Nar

``` # Load or create new YOLO model if isinstance(model, str): if model.endswith(".pt"): self._load(model) else: self._new(model) elif isinstance(model, Path): self._load(str(model)) ``` This code fixed the error.

I updated the functions. You can look at the readme file. ```python from whisperplus import SpeechToTextPipeline, download_youtube_to_mp3 url = "https://www.youtube.com/watch?v=di3rHkEZuUw" audio_path = download_youtube_to_mp3(url, output_dir="downloads", filename="test") ```

> Is there any progress on this? I don't have enough time to develop this. That's why this feature is not currently being developed. I will add it later.

You can use distiller-whisper models. Models: https://huggingface.co/distil-whisper 

I don't understand If you want to use the whisper model in real-time, you can look at this library. https://github.com/davabase/whisper_real_time

> Hi, I have worked with whisper models in real time transcription but the catch is in hls stream the video or audio is generated at a buffer of 6...

> If we are doing on a streaming service then it take buffer time of 6 sec. In real time we can clip second by second. I will research this...

Hi @Nishant-Kumar-2002 , can you review this code? This feature adds subtitles to the video.

> May I ask if the main idea is to implement real-time whisper to transcribe speech through the microphone or transcribe audio files in real-time to a file, so that...

@Nishant-Kumar-2002 Wonderful news 👍🏻 I'm waiting for the pull request.