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.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model authors have turned it off explicitly.