paraformer streaming bugfix

游雁

2024-03-18 cbe2ea7e07cbf364827bd89cefc42b3f643ea3be

 README_zh.md

@@ -106,7 +106,7 @@
from funasr import AutoModel
# paraformer-zh is a multi-functional asr model
# use vad, punc, spk or not as you need
model = AutoModel(model="paraformer-zh",  vad_model="fsmn-vad", punc_model="ct-punc-c", 
model = AutoModel(model="paraformer-zh",  vad_model="fsmn-vad", punc_model="ct-punc", 
                  # spk_model="cam++"
                  )
res = model.generate(input=f"{model.model_path}/example/asr_example.wav", 
@@ -210,6 +210,35 @@
```
更多详细用法（[示例](https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining)）

## 导出ONNX
### 从命令行导出
```shell
funasr-export ++model=paraformer ++quantize=false
```

### 从Python导出
```python
from funasr import AutoModel

model = AutoModel(model="paraformer")

res = model.export(quantize=False)
```

### 测试ONNX
```python
# pip3 install -U funasr-onnx
from funasr_onnx import Paraformer
model_dir = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
model = Paraformer(model_dir, batch_size=1, quantize=True)

wav_path = ['~/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav']

result = model(wav_path)
print(result)
```

更多例子请参考 [样例](runtime/python/onnxruntime)

<a name="服务部署"></a>
## 服务部署