Downloads · 30 days
0
ARMHuBERT
sungnyun/ARMHuBERT
ARMHuBERT is a automatic speech recognition model from sungnyun. Use it when you need speech turned into text. It is set up for fairseq. The card lists the license as apache-2.0.
Access
Public
Updated Oct 2, 2023
Repo size
4 GB
Likes
3
Public
Repo makeup
Click a slice to open those files.
.ckpt4 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- fairseq
- License
- apache-2.0
- Access
- Public
- Created
- Oct 2, 2023
- Updated
- Oct 2, 2023
- SHA
- 80496cd2
Model card
From the Hugging Face model README
<br>
<br>
ARMHuBERT Model Card
This repo contains the models from our paper Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation, INTERSPEECH 2023.
Model details
Model type: ARMHuBERT is an open-source speech SSL model distilled from HuBERT-Base, by attention map reusing and masking distillation. We also provide the model checkpoints of MaskHuBERT (without attention map reusing) and ARMwavLM (wavLM-Base teacher).
- Attention Map Reusing: Reuse previous layer's attention map to remove key & query parameters in Transformer.
- Masking Distillation: Masking distillation treating masked frames and unmasked frames separately.
License: Apache 2.0 License
Where to send questions or comments about the model: https://github.com/sungnyun/ARMHuBERT/issues
Training dataset
Pretraining data: LibriSpeech
[ModelName]-100h.ckpt: train-clean-100[ModelName]-960h.ckpt: train-clean-100 + train-clean-360 + train-other-500
More detials are in our github, https://github.com/sungnyun/ARMHuBERT.
- Task
- Automatic Speech Recognition
- Library
- fairseq
- License
- apache-2.0
- Languages
- en
- Created
- Oct 2, 2023
- Updated
- Oct 2, 2023