|
|
--- |
|
|
license: cc-by-nc-4.0 |
|
|
--- |
|
|
|
|
|
Model Checkpoint for [LauraTSE](https://github.com/Beilong-Tang/lauraTSE_code). |
|
|
|
|
|
We have trained it on LibriSpeech using Dynamic Mixing with SNR 0-5 dB for 100 epochs and then finetune it on Libri2Mix for 20 epochs. |
|
|
|
|
|
Results on Libri2Mix clean testset: |
|
|
|
|
|
| Model | SIG | BAK | OVRL | NISQA | SpeechBERT | dWER | WavLM Sim | Wespeaker Sim | |
|
|
| :------: | :---: | :---: | :---: | :---: | :--------: | :---: | :-------: | :-----------: | |
|
|
| LauraTSE | 3.609 | 4.084 | 3.336 | 4.333 | 0.908 | 0.159 | 0.974 | 0.876 | |
|
|
|
|
|
Please refer to [files](https://huggingface.co/Beilong/LauraTSE/tree/main) for model ckpt and config. |
|
|
|
