mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-09-19 05:54:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update results

Browse Source
This commit is contained in:
pkufool 2023-06-23 21:16:09 +08:00
parent ae47b739f0
commit 93dd3f5887
1 changed files with 85 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

85
egs/wenetspeech/ASR/RESULTS.md
View File

@ -1,5 +1,90 @@
## Results
### WenetSpeech char-based training results (Non-streaming and streaming) on zipformer model
This is the [pull request](https://github.com/k2-fsa/icefall/pull/1130) in icefall.
#### Non-streaming
Best results (num of params : ~76M):
Type | Greedy(dev & net & meeting) | Beam search(dev & net & meeting) |  
-- | -- | -- | --
Non-streaming | 7.36 & 7.65 & 12.43 | 7.32 & 7.61 & 12.35 | --epoch=12
The training command:
```
./zipformer/train.py \
--world-size 6 \
--num-epochs 12 \
--use-fp16 1 \
--max-duration 450 \
--training-subset L \
--lr-epochs 1.5 \
--context-size 2 \
--exp-dir zipformer/exp_L_context_2 \
--causal 0 \
--num-workers 8
```
Listed best results for each epoch below:
Epoch | Greedy search(dev & net & meeting) | Modified beam search(dev & net & meeting) |  
-- | -- | -- | --
4 | 7.83 & 8.86 &13.73 | 7.75 & 8.81 & 13.67 | avg=1;blank-penalty=2
5 | 7.75 & 8.46 & 13.38 | 7.68 & 8.41 & 13.27 | avg=1;blank-penalty=2
6 | 7.72 & 8.19 & 13.16 | 7.62 & 8.14 & 13.06 | avg=1;blank-penalty=2
7 | 7.59 & 8.08 & 12.97 | 7.53 & 8.01 & 12.87 | avg=2;blank-penalty=2
8 | 7.68 & 7.87 & 12.96 | 7.61 & 7.81 & 12.88 | avg=1;blank-penalty=2
9 | 7.57 & 7.77 & 12.87 | 7.5 & 7.71 & 12.77 | avg=1;blank-penalty=2
10 | 7.45 & 7.7 & 12.69 | 7.39 & 7.63 & 12.59 | avg=2;blank-penalty=2
11 | 7.35 & 7.67 & 12.46 | 7.31 & 7.63 & 12.43 | avg=3;blank-penalty=2
12 | 7.36 & 7.65 & 12.43 | 7.32 & 7.61 & 12.35 | avg=4;blank-penalty=2
The pre-trained model is available here : https://huggingface.co/pkufool/icefall-asr-zipformer-wenetspeech-20230615
#### Streaming
Best results (num of params : ~76M):
Type | Greedy(dev & net & meeting) | Beam search(dev & net & meeting) |  
-- | -- | -- | --
Streaming | 8.45 & 9.89 & 16.46 | 8.21 & 9.77 & 16.07 | --epoch=12; --chunk-size=16; --left-context-frames=256
Streaming | 8.0 & 9.0 & 15.11 | 7.84 & 8.94 & 14.92 | --epoch=12; --chunk-size=32; --left-context-frames=256
The training command:
```
./zipformer/train.py \
--world-size 8 \
--num-epochs 12 \
--use-fp16 1 \
--max-duration 450 \
--training-subset L \
--lr-epochs 1.5 \
--context-size 2 \
--exp-dir zipformer/exp_L_causal_context_2 \
--causal 1 \
--num-workers 8
```
Best results for each epoch (--chunk-size=16; --left-context-frames=128)
Epoch | Greedy search(dev & net & meeting) | Modified beam search(dev & net & meeting) |  
-- | -- | -- | --
6 | 9.14 & 10.75 & 18.15 | 8.79 & 10.54 & 17.64 | avg=1;blank-penalty=1.5
7 | 9.11 & 10.61 & 17.86 | 8.8 & 10.42 & 17.29 | avg=1;blank-penalty=1.5
8 | 8.89 & 10.32 & 17.44 | 8.59 & 10.09 & 16.9 | avg=1;blank-penalty=1.5
9 | 8.86 & 10.11 & 17.35 | 8.55 & 9.87 & 16.76 | avg=1;blank-penalty=1.5
10 | 8.66 & 10.0 & 16.94 | 8.39 & 9.83 & 16.47 | avg=2;blank-penalty=1.5
11 | 8.58 & 9.92 & 16.67 | 8.32 & 9.77 & 16.27 | avg=3;blank-penalty=1.5
12 | 8.45 & 9.89 & 16.46 | 8.21 & 9.77 & 16.07 | avg=4;blank-penalty=1.5
The pre-trained model is available here: https://huggingface.co/pkufool/icefall-asr-zipformer-streaming-wenetspeech-20230615
### WenetSpeech char-based training results (offline and streaming) (Pruned Transducer 5)
#### 2022-07-22