marcoyang
/

pruned_transducer_stateless6_hubert_xtralarge_ll60k_finetune_ls960

Model card Files Files and versions

This repository contains the codebook indexes generated by a fine-tuned HuBERT-XL model.

It can be used for multi-vector quantization knowledge distillation in ASR(https://arxiv.org/abs/2211.00508 for the paper). Please refer to https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/distillation_with_hubert.sh for usage instructions.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for marcoyang/pruned_transducer_stateless6_hubert_xtralarge_ll60k_finetune_ls960

Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation

Paper • 2211.00508 • Published Oct 31, 2022