雾聪
2024-03-14 0cf5dfec2c8313fc2ed2aab8d10bf3dc4b9c283f
README.md
@@ -215,17 +215,32 @@
### Command-line usage
```shell
funasr-export ++model=paraformer ++quantize=false
funasr-export ++model=paraformer ++quantize=false ++device=cpu
```
### python
### Python
```python
from funasr import AutoModel
model = AutoModel(model="paraformer")
model = AutoModel(model="paraformer", device="cpu")
res = model.export(quantize=False)
```
### Text 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)
```
More examples ref to [demo](runtime/python/onnxruntime)
## Deployment Service
FunASR supports deploying pre-trained or further fine-tuned models for service. Currently, it supports the following types of service deployment:
@@ -244,9 +259,9 @@
You can also scan the following DingTalk group or WeChat group QR code to join the community group for communication and discussion.
|DingTalk group |                     WeChat group                      |
|:---:|:-----------------------------------------------------:|
|<div align="left"><img src="docs/images/dingding.jpg" width="250"/> | <img src="docs/images/wechat.png" width="215"/></div> |
|                           DingTalk group                            |                     WeChat group                      |
|:-------------------------------------------------------------------:|:-----------------------------------------------------:|
| <div align="left"><img src="docs/images/dingding.png" width="250"/> | <img src="docs/images/wechat.png" width="215"/></div> |
## Contributors