Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add

游雁

2023-08-30 c2e4e3c2e9be855277d9f4fa9cd0544892ff829a

 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 +65,48 @@
|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, dataset_type: small, batch bins 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           |
| Full-tuning      | 1.62          |1.78           |

- Train config: 
  - Training data: 16k sichuan dialect
  - Training info: lr 0.0002, dataset_type: small, batch bins 2000, 2 gpu, acc_grad 1, 20 epochs
  - Decoding info: beam_size 1, average_num 10
  
  
|   model  | Training Data(h) | common cer(%) | sichuan cer(%) |
|:--------:|:-------------:|:-------:|:------------:|
| Pretrain |               |   8.57  |     19.81    |
| Full-tuning |      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, dataset_type: small, batch bins 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) | 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          |