Update results for tedlium3 pruned RNN-T (#307)

* Update README.md
This commit is contained in:
Mingshuang Luo 2022-04-11 22:19:26 +08:00 committed by GitHub
parent 93c60a9d30
commit 118e195004
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 2 additions and 2 deletions

View File

@ -176,7 +176,7 @@ The best WER using modified beam search with beam size 4 is:
| | dev | test |
|-----|-------|--------|
| WER | 6.72 | 6.12 |
| WER | 6.77 | 6.14 |
We provide a Colab notebook to run a pre-trained Pruned Transducer Stateless model: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1je_1zGrOkGVVd4WLzgkXRHxl-I27yWtz?usp=sharing)

View File

@ -12,7 +12,7 @@ The WERs are
|------------------------------------|------------|------------|------------------------------------------|
| greedy search | 7.27 | 6.69 | --epoch 29, --avg 13, --max-duration 100 |
| beam search (beam size 4) | 6.70 | 6.04 | --epoch 29, --avg 13, --max-duration 100 |
| modified beam search (beam size 4) | 6.77 | 6.12 | --epoch 29, --avg 13, --max-duration 100 |
| modified beam search (beam size 4) | 6.77 | 6.14 | --epoch 29, --avg 13, --max-duration 100 |
| fast beam search (set as default) | 7.14 | 6.50 | --epoch 29, --avg 13, --max-duration 1500|
The training command for reproducing is given below: