export model

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 @@ class Paraformer():
         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 @@ logger_initialized = {}
 
 
 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

@@ -1,31 +0,0 @@
-TokenIDConverter:
-  token_path: resources/models/token_list.pkl
-  unk_symbol: <unk>
-
-CharTokenizer:
-  symbol_value:
-  space_symbol: <space>
-  remove_non_linguistic_symbols: false
-
-WavFrontend:
-  cmvn_file: resources/models/am.mvn
-  frontend_conf:
-    fs: 16000
-    window: hamming
-    n_mels: 80
-    frame_length: 25
-    frame_shift: 10
-    lfr_m: 7
-    lfr_n: 6
-    filter_length_max: -.inf
-    dither: 0.0
-
-Model:
-  model_path: resources/models/model.onnx
-  use_cuda: false
-  CUDAExecutionProvider:
-      device_id: 0
-      arena_extend_strategy: kNextPowerOfTwo
-      cudnn_conv_algo_search: EXHAUSTIVE
-      do_copy_in_default_stream: true
-  batch_size: 3