FunASR

mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00

History

SWHL 69ee88f49b Add inference module support for onnxruntime		2023-02-11 15:41:09 +08:00
..
rapid_paraformer	Add inference module support for onnxruntime	2023-02-11 15:41:09 +08:00
resources	Add inference module support for onnxruntime	2023-02-11 15:41:09 +08:00
.gitignore	Add inference module support for onnxruntime	2023-02-11 15:41:09 +08:00
README.md	Add inference module support for onnxruntime	2023-02-11 15:41:09 +08:00
requirements.txt	Add inference module support for onnxruntime	2023-02-11 15:41:09 +08:00

README.md

Using paraformer with ONNXRuntime

Introduction

Model comes from speech_paraformer.

Steps:

Download the whole directory (funasr/runtime/python/onnxruntime) to the local.
Install the related packages.
```
pip install requirements.txt
```

Download the model.

Download Link

Put the model into the resources/models.

.
├── demo.py
├── rapid_paraformer
│   ├── __init__.py
│   ├── kaldifeat
│   ├── __pycache__
│   ├── rapid_paraformer.py
│   └── utils.py
├── README.md
├── requirements.txt
├── resources
│   ├── config.yaml
│   └── models
│       ├── am.mvn
│       ├── model.onnx  # Put it here.
│       └── token_list.pkl
├── test_onnx.py
├── tests
│   ├── __pycache__
│   └── test_infer.py
└── test_wavs
    ├── 0478_00017.wav
    └── asr_example_zh.wav

Run the demo.

Input: wav formt file, support formats: str, np.ndarray, List[str]
Output: List[str]: recognition result.

Example:

from rapid_paraformer import RapidParaformer


config_path = 'resources/config.yaml'
paraformer = RapidParaformer(config_path)

wav_path = ['test_wavs/0478_00017.wav']

result = paraformer(wav_path)
print(result)