Saad Nadeem
Saad Nadeem
Really need the on-progress event.
> renderEditor Maybe wrap into a proper function like passing JSON object etc. Just make a wrapper function for it. It will help others a lot. With this approach, you...
Hi, any update on serving faster-whisper via VLLM?
Thanks for responding. I am using v2.0.4 and pulled directly from docker hub 2 hours ago.
> The reverse would also be useful , CPU to GPU. > > The use case being memory snapshots when running parallel processing. I am trying exactly same thing. 'FasterWhisperPipeline'...
Any update on this? He is asking to keep the model loaded in memory so for every inference the model does not have to be loaded again as it time...
Still not implemented.
> ```ts > client_type: ClientType.TV_EMBEDDED, > retrieve_player: false, > generate_session_locally: true, > device_category: 'mobile', > ``` I tried this, with these settings it always failed with "message: Request to https://www.youtube.com/youtubei/v1/pla…prettyPrint=false&alt=json...