readme

游雁

2023-03-24 0f49a81391dbf222853f445d91673a3fd582687e

 funasr/runtime/python/libtorch/README.md

@@ -1,5 +1,6 @@
## Using paraformer with libtorch
## Using funasr with libtorch

[FunASR](https://github.com/alibaba-damo-academy/FunASR) hopes to build a bridge between academic research and industrial applications on speech recognition. By supporting the training & finetuning of the industrial-grade speech recognition model released on ModelScope, researchers and developers can conduct research and production of speech recognition models more conveniently, and promote the development of speech recognition ecology. ASR for Fun！

### Introduction
- Model comes from [speech_paraformer](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary).
@@ -7,13 +8,6 @@
### Steps:
1. Export the model.
   - Command: (`Tips`: torch >= 1.11.0 is required.)

      ```shell
      python -m funasr.export.export_model [model_name] [export_dir] false
      ```
      `model_name`: the model is to export.

      `export_dir`: the dir where the onnx is export.

       More details ref to ([export docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/export))

@@ -29,10 +23,7 @@

2. Install the `funasr_torch`.
    ```shell
    git clone https://github.com/alibaba/FunASR.git && cd FunASR
    cd funasr/runtime/python/libtorch
    python setup.py build
    python setup.py install
    pip install funasr_torch -i https://pypi.Python.org/simple
    ```


@@ -66,3 +57,4 @@
|   Onnx   |   0.038    |

## Acknowledge
This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR).