jmwang66 0b8348376a update FunASR version==0.1.4		%!s(int64=3) %!d(string=hai) anos
..
conf	0b8348376a update FunASR version==0.1.4	%!s(int64=3) %!d(string=hai) anos
modelscope_utils	0b8348376a update FunASR version==0.1.4	%!s(int64=3) %!d(string=hai) anos
utils	0b8348376a update FunASR version==0.1.4	%!s(int64=3) %!d(string=hai) anos
README.md	0b8348376a update FunASR version==0.1.4	%!s(int64=3) %!d(string=hai) anos
modelscope_common_finetune.sh	0b8348376a update FunASR version==0.1.4	%!s(int64=3) %!d(string=hai) anos
modelscope_common_infer.sh	0b8348376a update FunASR version==0.1.4	%!s(int64=3) %!d(string=hai) anos
modelscope_common_infer_after_finetune.sh	0b8348376a update FunASR version==0.1.4	%!s(int64=3) %!d(string=hai) anos
path.sh	0b8348376a update FunASR version==0.1.4	%!s(int64=3) %!d(string=hai) anos

ModelScope Model

How to finetune and infer using a pretrained ModelScope Model

Modify finetune training related parameters in conf/train_asr_uniasr_40e1_12d1_20e2_12d2_1280_320_lfr6.yaml
Setting parameters in modelscope_common_finetune.sh
- dataset: the dataset dir needs to include files: train/wav.scp, train/text; optional dev/wav.scp, dev/text, test/wav.scp test/text
- tag: exp tag
- init_model_name: speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online # pre-trained model, download from modelscope during fine-tuning
Then you can run the pipeline to finetune with our model download from modelscope:
```
sh ./modelscope_common_finetune.sh
```

Or you can use the finetuned model for inference directly.

Setting parameters in modelscope_common_infer.sh
- data_dir: # wav list, ${data_dir}/wav.scp
- exp_dir: the result path
- model_name: speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online # pre-trained model, download from modelscope
Then you can run the pipeline to infer with:
```
sh ./modelscope_common_infer.sh
```