Merge pull request #770 from alibaba-damo-academy/dev_lhn

hnluo

2023-07-21 3aef6df36d182f7e41e522805a96127f504eda5d

Merge pull request #770 from alibaba-damo-academy/dev_lhn

Dev lhn

 egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/RESULTS.md

@@ -78,7 +78,7 @@
| model    | dev cer(%) | test cer(%) |
|:---------:|:-------------:|:-------------:|
| Pretrain       | 1.75          |1.95           |
| Finetune      | 1.62          |1.78           |
| Full-tuning      | 1.62          |1.78           |

- Train config: 
  - Training data: 16k sichuan dialect
@@ -86,10 +86,10 @@
  - Decoding info: beam_size 1, average_num 10
  
  
|   model  | Training Data(h) | cn cer(%) | sichuan cer(%) |
|   model  | Training Data(h) | common cer(%) | sichuan cer(%) |
|:--------:|:-------------:|:-------:|:------------:|
| Pretrain |               |   8.57  |     19.81    |
| Finetune |      50      |   8.8   |      12      |
| Full-tuning |      50      |   8.8   |      12      |
|          |      100     |   9.24  |     11.63    |
|          |      200     |   9.82  |     10.47    |
|          |      300     |   9.95  |     10.44    |
@@ -103,12 +103,10 @@
  - Lora info: lora_bias: "all", lora_list ['q','v'], lora_rank:8, lora_alpha:16, lora_dropout:0.1
  - Decoding info: beam_size 1, average_num 10
  
|     model     | Training Data(h) | Trainable Parameters(M) | cn cer(%) | sichuan cer(%) |
|:-------------:|:----------------:|:-----------------------:|:---------:|:--------------:|
|    Pretrain   |                  |                         |    8.57   |      19.81     |
|               |                  |                         |           |                |
|    Finetune   |        50        |          220.9          |    8.8    |       12       |
| Lora Finetune |        50        |           2.29          |    9.13   |      12.13     |
|               |                  |                         |           |                |
|    Finetune   |        200       |          220.9          |    9.82   |      10.47     |
| Lora Finetune |        200       |           2.29          |    9.21   |      11.28     |
| model         | Training Data(h) | Trainable Parameters(M) | Memory Usage(G) | common cer(%) | sichuan cer(%) |
|:---------------:|:------------------:|:-------------------------:|:-----------------:|:---------------:|:----------------:|
| Pretrain      |                  |                         |                 | 8.57          | 19.81          |
| Full-tuning   | 50               | 220.9                   | 15              | 8.8           | 12             |
| Lora Finetune | 50               | 2.29                    | 7               | 9.13          | 12.13          |
| Full-tuning   | 200              | 220.9                   | 15              | 9.82          | 10.47          |
| Lora Finetune | 200              | 2.29                    | 7               | 9.21          | 11.28          |