mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-12-09 14:05:33 +00:00
* Replace deprecated pytorch methods
- torch.cuda.amp.GradScaler(...) => torch.amp.GradScaler("cuda", ...)
- torch.cuda.amp.autocast(...) => torch.amp.autocast("cuda", ...)
* Replace `with autocast(...)` with `with autocast("cuda", ...)`
Co-authored-by: Li Peng <lipeng@unisound.ai>
Introduction
This recipe includes some different ASR models trained with Alimeeting (far).
./RESULTS.md contains the latest results.
Transducers
There are various folders containing the name transducer in this folder.
The following table lists the differences among them.
| Encoder | Decoder | Comment | |
|---|---|---|---|
pruned_transducer_stateless2 |
Conformer(modified) | Embedding + Conv1d | Using k2 pruned RNN-T loss |
The decoder in transducer_stateless is modified from the paper
Rnn-Transducer with Stateless Prediction Network.
We place an additional Conv1d layer right after the input embedding layer.