游雁
2023-02-13 05bb36b186ad6cbb7f22ab157b065a3f75c3412b
export model
3个文件已修改
3个文件已删除
73 ■■■■■ 已修改文件
funasr/runtime/python/onnxruntime/paraformer/README.md 28 ●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/runtime/python/onnxruntime/paraformer/rapid_paraformer/paraformer_onnx.py 2 ●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/runtime/python/onnxruntime/paraformer/rapid_paraformer/utils.py 4 ●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/runtime/python/onnxruntime/paraformer/resources/config.yaml 31 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/runtime/python/onnxruntime/paraformer/resources/models/am.mvn 8 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/runtime/python/onnxruntime/paraformer/resources/models/token_list.pkl 补丁 | 查看 | 原始文档 | blame | 历史
funasr/runtime/python/onnxruntime/paraformer/README.md
@@ -17,26 +17,7 @@
   ```
3.  Export the model.
    - Export your model([docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/export)), or [Download Link](https://swap.oss-cn-hangzhou.aliyuncs.com/zhifu.gzf/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.onnx?OSSAccessKeyId=LTAI4FxMqzhBUx5XD4mKs296&Expires=2036094510&Signature=agmtMkxLEviGg3Rt3gOO4PvfrJY%3D)
    - Put the model into the `resources/models`.
        ```text
        .
        ├── demo.py
        ├── rapid_paraformer
        │   ├── __init__.py
        │   ├── kaldifeat
        │   ├── __pycache__
        │   ├── rapid_paraformer.py
        │   └── utils.py
        ├── README.md
        ├── requirements.txt
        ├── test_onnx.py
        ├── tests
        │   ├── __pycache__
        │   └── test_infer.py
        └── test_wavs
            ├── 0478_00017.wav
            └── asr_example_zh.wav
        ```
4. Run the demo.
   - Input: wav formt file, support formats: `str, np.ndarray, List[str]`
   - Output: `List[str]`: recognition result.
@@ -44,11 +25,10 @@
        ```python
        from paraformer_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)
        config_path = 'resources/config.yaml'
        model = Paraformer(config_path)
        wav_path = ['example/asr_example.wav']
        wav_path = ['/nfs/zhifu.gzf/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav']
        result = model(wav_path)
        print(result)
funasr/runtime/python/onnxruntime/paraformer/rapid_paraformer/paraformer_onnx.py
@@ -137,7 +137,7 @@
        texts = sentence_postprocess(token)
        text = texts[0]
        # text = self.tokenizer.tokens2text(token)
        return text[:valid_token_num-1]
        return text
if __name__ == '__main__':
funasr/runtime/python/onnxruntime/paraformer/rapid_paraformer/utils.py
@@ -22,8 +22,8 @@
class TokenIDConverter():
    def __init__(self, token_list: Union[Path, str],
                 unk_symbol: str = "<unk>",):
    def __init__(self, token_list: Union[List, str],
                 ):
        check_argument_types()
        # self.token_list = self.load_token(token_path)
funasr/runtime/python/onnxruntime/paraformer/resources/config.yaml
File was deleted
funasr/runtime/python/onnxruntime/paraformer/resources/models/am.mvn
File was deleted
funasr/runtime/python/onnxruntime/paraformer/resources/models/token_list.pkl
Binary files differ