v0.3.1

游雁

2023-03-24 4dc5bd63a2aa4a93beadacaf88768dc78cf4c0eb

 funasr/runtime/python/onnxruntime/README.md

@@ -11,7 +11,7 @@

### Steps:
1. Export the model.
   - Command: (`Tips`: torch 1.11.0 is required.)
   - Command: (`Tips`: torch >= 1.11.0 is required.)

      ```shell
      python -m funasr.export.export_model [model_name] [export_dir] [true]
@@ -24,24 +24,24 @@

       - `e.g.`, Export model from modelscope
         ```shell
         python -m funasr.export.export_model 'damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch' "./export" true
         python -m funasr.export.export_model --model-name damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize False
         ```
       - `e.g.`, Export model from local path, the model'name must be `model.pb`.
         ```shell
         python -m funasr.export.export_model '/mnt/workspace/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch' "./export" true
         python -m funasr.export.export_model --model-name ./damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize False
         ```


2. Install the `rapid_paraformer`.
   - Build the rapid_paraformer `whl`
2. Install the `funasr_onnx`.
   - Build the funasr_onnx `whl`
     ```shell
     git clone https://github.com/alibaba/FunASR.git && cd FunASR
     cd funasr/runtime/python/onnxruntime/rapid_paraformer
     cd funasr/runtime/python/onnxruntime
     python setup.py bdist_wheel
     ```
   - Install the build `whl`
     ```bash
     pip install dist/rapid_paraformer-0.0.1-py3-none-any.whl
     pip install dist/funasr_onnx-0.0.2-py3-none-any.whl
     ```

3. Run the demo.
@@ -50,7 +50,7 @@
   - Output: `List[str]`: recognition result.
   - Example:
        ```python
        from rapid_paraformer import Paraformer
        from funasr_onnx import Paraformer

        model_dir = "/nfs/zhifu.gzf/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
        model = Paraformer(model_dir, batch_size=1)