update

嘉渊

2023-04-25 2a3336d9a8a9d74662be805510abdd0a29414ae5

 funasr/runtime/python/libtorch/README.md

@@ -1,5 +1,6 @@
## 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).
@@ -21,10 +22,19 @@


2. Install the `funasr_torch`.
    
    install from pip
    ```shell
    pip install funasr_torch -i https://pypi.Python.org/simple
    pip install --upgrade funasr_torch -i https://pypi.Python.org/simple
    ```
    or install from source code

    ```shell
    git clone https://github.com/alibaba/FunASR.git && cd FunASR
    cd funasr/runtime/python/libtorch
    python setup.py build
    python setup.py install
    ```

3. Run the demo.
   - Model_dir: the model path, which contains `model.torchscripts`, `config.yaml`, `am.mvn`.
@@ -43,6 +53,10 @@
        print(result)
        ```

## Performance benchmark

Please ref to [benchmark](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/python/benchmark_libtorch.md)

## Speed

Environment：Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz
@@ -56,3 +70,4 @@
|   Onnx   |   0.038    |

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