mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-08 09:32:20 +00:00
Update results for transducer_stateless after training for more epochs. (#207)
This commit is contained in:
parent
ac7c2d84bc
commit
72f838dee1
@ -84,7 +84,7 @@ The best WER using modified beam search with beam size 4 is:
|
||||
|
||||
| | test-clean | test-other |
|
||||
|-----|------------|------------|
|
||||
| WER | 2.67 | 6.64 |
|
||||
| WER | 2.67 | 6.57 |
|
||||
|
||||
Note: No auxiliary losses are used in the training and no LMs are used
|
||||
in the decoding.
|
||||
|
@ -61,10 +61,10 @@ The WERs are
|
||||
|
||||
| | test-clean | test-other | comment |
|
||||
|-------------------------------------|------------|------------|------------------------------------------|
|
||||
| greedy search (max sym per frame 1) | 2.68 | 6.71 | --epoch 61, --avg 18, --max-duration 100 |
|
||||
| greedy search (max sym per frame 2) | 2.69 | 6.71 | --epoch 61, --avg 18, --max-duration 100 |
|
||||
| greedy search (max sym per frame 3) | 2.69 | 6.71 | --epoch 61, --avg 18, --max-duration 100 |
|
||||
| modified beam search (beam size 4) | 2.67 | 6.64 | --epoch 61, --avg 18, --max-duration 100 |
|
||||
| greedy search (max sym per frame 1) | 2.67 | 6.67 | --epoch 63, --avg 19, --max-duration 100 |
|
||||
| greedy search (max sym per frame 2) | 2.67 | 6.67 | --epoch 63, --avg 19, --max-duration 100 |
|
||||
| greedy search (max sym per frame 3) | 2.67 | 6.67 | --epoch 63, --avg 19, --max-duration 100 |
|
||||
| modified beam search (beam size 4) | 2.67 | 6.57 | --epoch 63, --avg 19, --max-duration 100 |
|
||||
|
||||
|
||||
The training command for reproducing is given below:
|
||||
@ -90,8 +90,8 @@ The tensorboard training log can be found at
|
||||
|
||||
The decoding command is:
|
||||
```
|
||||
epoch=61
|
||||
avg=18
|
||||
epoch=63
|
||||
avg=19
|
||||
|
||||
## greedy search
|
||||
for sym in 1 2 3; do
|
||||
|
Loading…
x
Reference in New Issue
Block a user