Pretrained Models in WeNet
We provide two types of pretrained model in WeNet to facilitate users with different requirements.
Checkpoint Model, with suffix .pt, the model trained and saved as checkpoint by WeNet python code, you can reproduce our published result with it, or you can use it as checkpoint to continue.
Runtime Model, with suffix .zip, you can directly use
runtime modelin our x86 or android runtime, the
runtime modelis export by Pytorch JIT on the
checkpoint model. And the runtime models has been quantized to reduce the model size and network traffic.
The pretrained model in WeNet follows the license of it’s corresponding dataset.
For example, the pretrained model on LibriSpeech follows
CC BY 4.0, since it is used as license of the LibriSpeech dataset, see http://openslr.org/12/.
Here is a list of the pretrained models on different datasets.
For non-Chinese users, please visit Pretrained Models(En) to download.
|Datasets||Languages||Checkpoint Model||Runtime Model||Contributor|