mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 18:12:19 +00:00
bb7f6ed6b7
* Add modified beam search for pruned rnn-t. * Fix style issues. * Update RESULTS.md. * Fix typos. * Minor fixes. * Test the pre-trained model using GitHub actions. * Let the user install optimized_transducer on her own. * Fix errors in GitHub CI.
23 lines
1.4 KiB
Markdown
23 lines
1.4 KiB
Markdown
|
|
# Introduction
|
|
|
|
Please refer to <https://icefall.readthedocs.io/en/latest/recipes/librispeech/index.html>
|
|
for how to run models in this recipe.
|
|
|
|
# Transducers
|
|
|
|
There are various folders containing the name `transducer` in this folder.
|
|
The following table lists the differences among them.
|
|
|
|
| | Encoder | Decoder | Comment |
|
|
|---------------------------------------|-----------|--------------------|---------------------------------------------------|
|
|
| `transducer` | Conformer | LSTM | |
|
|
| `transducer_stateless` | Conformer | Embedding + Conv1d | |
|
|
| `transducer_lstm` | LSTM | LSTM | |
|
|
| `transducer_stateless_multi_datasets` | Conformer | Embedding + Conv1d | Using data from GigaSpeech as extra training data |
|
|
| `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.
|