Skip to content

Releases: RF5/transfusion-asr

PyPi transfusion-asr release

27 Sep 08:16
Compare
Choose a tag to compare
Pre-release

Added code release to PyPi

Transfusion may now be installed with pip:

pip install transfusion-asr

Model checkpoints

13 Oct 09:28
@RF5 RF5
e46b60b
Compare
Choose a tag to compare

This release contains the checkpoints of:

  • The frozen WavLM encoder (taken from the the original microsoft repo https://github.com/microsoft/unilm/tree/master/wavlm), please see the original WavLM paper (https://arxiv.org/abs/2110.13900) from the original authors for more details on this.
  • The best TransFusion model described in our paper (462k updates, which is 3.7M steps given our gradient accumulation setup).
  • The letter vocabulary used to convert indices to characters and vice versa.
  • The full original checkpoint of the best model described in the paper (in case you wish to fine-tune from this model). Because it is too large, it is split into multiple parts (mp_rank_00_model_states.pt.part*). Please download each part (all the .pt.part* files), and concatenate them together with cat mp_rank_00_model_states.pt.part* > mp_rank_00_model_states.pt. This is the full checkpoint associated with transfusion_462k_slim.pt. The full concatenated checkpoint has md5 checksum: b7465223b1c688cc6c723872f7ada54c