FunASR/funasr/runtime/python/onnxruntime/paraformer/README.md

Using paraformer with ONNXRuntime

Introduction

• Model comes from speech_paraformer.

Steps:

1. Download the whole directory (funasr/runtime/python/onnxruntime) to the local.

2. Install the related packages.

   pip install requirements.txt
   

3. Export the model.

   • Export your model(docs), or Download Link

4. Run the demo.

   • Model_dir: the root path, which contains model.onnx, config.yaml, am.mvn.
   • Input: wav formt file, support formats: str, np.ndarray, List[str]
   • Output: List[str]: recognition result.
   • Example:

     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)
     
     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)
     

Acknowledge

1. We acknowledge SWHL for contributing the onnxruntime(python api).