mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 10:02:22 +00:00
parent
93c60a9d30
commit
118e195004
@ -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: [](https://colab.research.google.com/drive/1je_1zGrOkGVVd4WLzgkXRHxl-I27yWtz?usp=sharing)
|
||||
|
||||
|
@ -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:
|
||||
|
Loading…
x
Reference in New Issue
Block a user