mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-08 09:32:20 +00:00
* Ignore padding frames during RNN-T decoding. * Fix outdated decoding code. * Minor fixes.
Introduction
This recipe includes some different ASR models trained with TedLium3.
Transducers
There are various folders containing the name transducer
in this folder.
The following table lists the differences among them.
Encoder | Decoder | Comment | |
---|---|---|---|
transducer_stateless |
Conformer | Embedding + Conv1d | |
pruned_transducer_stateless |
Conformer | 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.