Search found 2 matches

Author Message

dkhold

Post 11-Aug-2024 17:56

All wav2vec 2.0 pre-trained models from torchaudio pipelines, including VoxPopuli and XLS-R.
Does not include HuBERT and WaveLM.
https://pytorch.org/audio/stable/pipelines.html#id3

leaf

Post 12-Jun-2024 06:11

New category for STT please or Whisper :)
This torrent contains safetensors weights of OpenAI's Whisper Large v3 model, in fp16 precision. All files are cloned from the HuggingFace repo here: https://huggingface.co/openai/whisper-large-v3
 

Current time is: 14-Sep 15:16

All times are UTC + 1

Cover our bill…

Donate at ko-fi.com

Or use crypto:

We accept BTC, XMR, LTC, BCH & DOGE