mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-08 09:32:20 +00:00
8cb727e24a
* update tedlium3-pruned-transducer-stateless-codes * update README.md * update README.md * add fast beam search for decoding * do a change for RESULTS.md * do a change for RESULTS.md * do a fix * do some changes for pruned RNN-T
19 lines
896 B
Markdown
19 lines
896 B
Markdown
|
|
# 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](https://ieeexplore.ieee.org/document/9054419/).
|
|
We place an additional Conv1d layer right after the input embedding layer.
|