mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-08 09:32:20 +00:00
* fix a bug about the model_avg during finetuning by exchanging the order of loading pre-trained model and initializing avg model * only match the exact module prefix
Introduction
This recipe includes some different ASR models trained with WenetSpeech.
./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 |
pruned_transducer_stateless5 |
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.