mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 18:12:19 +00:00
7100c33820
* Add pruned RNN-T for aishell. * support torch script. * Update CI. * Minor fixes. * Add links to sherpa.
24 lines
1.4 KiB
Markdown
24 lines
1.4 KiB
Markdown
|
|
# Introduction
|
|
|
|
Please refer to <https://icefall.readthedocs.io/en/latest/recipes/aishell/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_stateless` | Conformer | Embedding + Conv1d | with `k2.rnnt_loss` |
|
|
| `transducer_stateless_modified` | Conformer | Embedding + Conv1d | with modified transducer from `optimized_transducer` |
|
|
| `transducer_stateless_modified-2` | Conformer | Embedding + Conv1d | with modified transducer from `optimized_transducer` + extra data |
|
|
| `pruned_transducer_stateless3` | Conformer (reworked) | Embedding + Conv1d | pruned RNN-T + reworked model with random combiner + using aidatatang_20zh as extra data|
|
|
|
|
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.
|