The Fuyu model was created by ADEPT, and authored by Rohan Bavishi, Erich Elsen, Curtis Hawthorne, Maxwell Nye, Augustus Odena, Arushi Somani, Sağnak Taşırlar. Add WhisperForCausalLM for speculative decoding by in #27195.Joint work from and Improve Encoder Decoder by in #26701 ![]() For details on using the model, refer to the following instructions. It only copies 2 decoder layers, which significantly reduces the time taken to auto-regressively generate text tokens:ĭistil-Whisper is MIT licensed and directly available in the Transformers library with chunked long-form inference, Flash Attention 2 support, and Speculative Decoding. ![]() It was proposed in the paper Robust Knowledge Distillation via Large-Scale Pseudo Labelling.ĭistil-Whisper copies the entire encoder from Whisper, meaning it retains Whisper's robustness to different audio conditions. Distil-Whisper is a distilled version of Whisper that is 6 times faster, 49% smaller, and performs within 1% word error rate (WER) on out-of-distribution data.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |