Update RESULTS.md

hnluo

2023-07-21 ad9b406821dbdd9e4922f90a26ce1712de6cd65a

Update RESULTS.md

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

@@ -2,14 +2,6 @@
- Model link: <https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary>
- Model size: 220M

# Environments
- date: `Tue Nov 22 18:48:39 CST 2022`
- python version: `3.7.12`
- FunASR version: `0.1.0`
- pytorch version: `pytorch 1.7.0`
- Git hash: ``
- Commit date: ``

# Beachmark Results

## AISHELL-1
@@ -73,3 +65,50 @@
|SPEECHIO_ASR_ZH000013| 2.57 | 2.25 |
|SPEECHIO_ASR_ZH000014| 3.86 | 3.08 |
|SPEECHIO_ASR_ZH000015| 3.34 | 2.67 |


# Fine-tuning Results

## Fine-tuning
- Train config: 
  - Training data: aishell-1
  - Training info: lr 0.0002, batch size 2000, 2 gpu, acc_grad 1, 20 epochs
  - Decoding info: beam_size 1, average_num 10

| model    | dev cer(%) | test cer(%) |
|:---------:|:-------------:|:-------------:|
| Pretrain       | 1.75          |1.95           |
| Finetune      | 1.62          |1.78           |

- Train config: 
  - Training data: 16k sichuan dialect
  - Training info: lr 0.0002, batch size 2000, 2 gpu, acc_grad 1, 20 epochs
  - Decoding info: beam_size 1, average_num 10
  
  
|   model  | Training Data(h) | cn cer(%) | sichuan cer(%) |
|:--------:|:-------------:|:-------:|:------------:|
| Pretrain |               |   8.57  |     19.81    |
| Finetune |      50      |   8.8   |      12      |
|          |      100     |   9.24  |     11.63    |
|          |      200     |   9.82  |     10.47    |
|          |      300     |   9.95  |     10.44    |
|          |     1000     |   9.99  |     9.78     |


## Lora Fine-tuning
- Train config: 
  - Training data: 16k sichuan dialect
  - Training info: lr 0.0002, batch size 2000, 2 gpu, acc_grad 1, 20 epochs
  - 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     |