Update RESULTS.md

hnluo

2023-07-21 fdce4df4314273060e762b75e73e0fb0811ed937

 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
@@ -89,7 +89,7 @@
|   model  | Training Data(h) | cn 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    |
@@ -107,8 +107,8 @@
|:-------------:|:----------------:|:-----------------------:|:---------:|:--------------:|
|    Pretrain   |                  |                         |    8.57   |      19.81     |
|               |                  |                         |           |                |
|    Finetune   |        50        |          220.9          |    8.8    |       12       |
|    Full-tuning   |        50        |          220.9          |    8.8    |       12       |
| Lora Finetune |        50        |           2.29          |    9.13   |      12.13     |
|               |                  |                         |           |                |
|    Finetune   |        200       |          220.9          |    9.82   |      10.47     |
|    Full-tuning   |        200       |          220.9          |    9.82   |      10.47     |
| Lora Finetune |        200       |           2.29          |    9.21   |      11.28     |