mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-09-04 06:34:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update RESULTS

Browse Source
This commit is contained in:
Guanbo Wang 2022-04-06 20:53:47 -04:00
parent f857d5a9ea
commit e56d32728d
2 changed files with 54 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
egs/gigaspeech/ASR/README.md
View File

@ -13,6 +13,8 @@ ln -sfv /path/to/GigaSpeech download/GigaSpeech
```
## Performance Record
| |Dev|Test|
|---|---|---|
|WER |11.92|11.85|
| | Dev | Test |
|-----|-------|-------|
| WER | 11.93 | 11.86 |
See [RESULTS](/egs/gigaspeech/ASR/RESULTS.md) for details.

49
egs/gigaspeech/ASR/RESULTS.md Normal file
View File

@ -0,0 +1,49 @@
## Results
### GigaSpeech BPE training results (Conformer-CTC)
#### 2022-04-06
The best WER, as of 2022-04-06, for the gigaspeech is below
(using HLG decoding + n-gram LM rescoring + attention decoder rescoring):
| | Dev | Test |
|-----|-------|-------|
| WER | 11.93 | 11.86 |
Scale values used in n-gram LM rescoring and attention rescoring for the best WERs are:
| ngram_lm_scale | attention_scale |
|----------------|-----------------|
| 0.3 | 1.5 |
To reproduce the above result, use the following commands for training:
```
cd egs/gigaspeech/ASR/conformer_ctc
./prepare.sh
export CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
./conformer_ctc/train.py \
--max-duration 120 \
--num-workers 1 \
--world-size 8 \
--exp-dir conformer_ctc/exp_500 \
--lang-dir data/lang_bpe_500
```
and the following command for decoding
```
./conformer_ctc/decode.py \
--epoch 19 \
--avg 8 \
--method attention-decoder \
--num-paths 1000 \
--exp-dir conformer_ctc/exp_500 \
--lang-dir data/lang_bpe_500 \
--max-duration 20 \
--num-workers 1
```
The tensorboard log for training is available at
<https://tensorboard.dev/experiment/rz63cmJXSK2fV9GceJtZXQ/>