mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-09-07 08:04:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Minor fixes.

Browse Source
This commit is contained in:
Fangjun Kuang 2022-05-23 14:38:00 +08:00
parent a896d982ec
commit 478bc42910
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
egs/librispeech/ASR/README.md
View File

@ -20,7 +20,7 @@ The following table lists the differences among them.
| `pruned_transducer_stateless2` | Conformer(modified) | Embedding + Conv1d | Using k2 pruned RNN-T loss |
| `pruned_transducer_stateless3` | Conformer(modified) | Embedding + Conv1d | Using k2 pruned RNN-T loss + using GigaSpeech as extra training data |
| `pruned_transducer_stateless4` | Conformer(modified) | Embedding + Conv1d | same as pruned_transducer_stateless2 + save averaged models periodically during training |
| `pruned_transducer_stateless5` | Conformer(modified) | Embedding + Conv1d | Using k2 pruned RNN-T loss + more layers + Random combiner|
| `pruned_transducer_stateless5` | Conformer(modified) | Embedding + Conv1d | same as pruned_transducer_stateless4 + more layers + random combiner|
The decoder in `transducer_stateless` is modified from the paper

2
egs/librispeech/ASR/RESULTS.md
View File

@ -135,7 +135,7 @@ results at:
#### Baseline-2
It has 88.98 M parameters. Compared to the model in pruned_transducer_stateless2, its more
It has 88.98 M parameters. Compared to the model in pruned_transducer_stateless2, its has more
layers (24 v.s 12) but a narrower model (1536 feedforward dim and 384 encoder dim vs 2048 feed forward dim and 512 encoder dim).
| | test-clean | test-other | comment |