Update python README

.github/workflows/gen_whl_to_pypi.yml

@@ -2,12 +2,14 @@ name: Push rapid_paraformer to pypi
 
 on:
   push:
-    branches: [ main ]
-    paths:
-      - 'python/rapid_paraformer/**'
-      - 'python/docs/doc_whl.md'
-      - 'python/setup.py'
-      - '.github/workflows/gen_whl_to_pypi.yml'
+    # branches: [ main ]
+    # paths:
+    #   - 'python/rapid_paraformer/**'
+    #   - 'python/docs/doc_whl.md'
+    #   - 'python/setup.py'
+    #   - '.github/workflows/gen_whl_to_pypi.yml'
+    tags:
+      - v*
 
 # env:
 #   RESOURCES_URL: https://github.com/RapidAI/RapidLatexOCR/releases/download/v0.0.0/models.zip
@@ -59,7 +61,7 @@ jobs:
           pip install -r requirements.txt
           python -m pip install --upgrade pip
           pip install wheel get_pypi_latest_version
-          python setup.py bdist_wheel ${{ github.event.head_commit.message }}
+          python setup.py bdist_wheel ${{ github.ref_name }}
 
       # - name: Publish distribution 📦 to Test PyPI
       #   uses: pypa/[email protected]

README.md

@@ -3,7 +3,7 @@
     <a href="https://huggingface.co/spaces/SWHL/RapidASRDemo" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Hugging Face Demo-blue"></a>
     <a href="https://www.modelscope.cn/studios/liekkas/RapidASRDemo/summary" target="_blank"><img src="https://img.shields.io/badge/ModelScope-Demo-blue"></a>
     <a href=""><img src="https://img.shields.io/badge/OS-Linux%2C%20Win%2C%20Mac-pink.svg"></a>
-    <a href=""><img src="https://img.shields.io/badge/Python->=3.6,<3.12-aff.svg"></a>
+    <a href=""><img src="https://img.shields.io/badge/Python->=3.6,<3.13-aff.svg"></a>
     <a href=""><img src="https://img.shields.io/badge/C++-aff.svg"></a>
 </p>
 

python/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

python/README.md

@@ -1,60 +1,71 @@
-## rapid_paraformer
-
-<p align="left">
-    <a href=""><img src="https://img.shields.io/badge/OS-Linux%2C%20Win%2C%20Mac-pink.svg"></a>
-    <a href=""><img src="https://img.shields.io/badge/Python->=3.6,<3.12-aff.svg"></a>
-    <a href="https://pepy.tech/project/rapid_paraformer"><img src="https://static.pepy.tech/personalized-badge/rapid_paraformer?period=total&units=abbreviation&left_color=grey&right_color=blue&left_text=Downloads"></a>
-    <a href="https://pypi.org/project/rapid_paraformer/"><img alt="PyPI" src="https://img.shields.io/pypi/v/rapid_paraformer"></a>
-    <a href="https://semver.org/"><img alt="SemVer2.0" src="https://img.shields.io/badge/SemVer-2.0-brightgreen"></a>
-    <a href="https://github.com/psf/black"><img src="https://img.shields.io/badge/code%20style-black-000000.svg"></a>
-</p>
-
-- 模型出自阿里达摩院[Paraformer语音识别-中文-通用-16k-离线-large-pytorch](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)
-- 🎉该项目核心代码已经并入[FunASR](https://github.com/alibaba-damo-academy/FunASR)
-- 本仓库仅对模型做了转换，只采用ONNXRuntime推理引擎
-
-#### TODO
+<div align="center">
+<div align="center">
+    <h1><b>Rapid Paraformer</b></h1>
+</div>
+
+<a href=""><img src="https://img.shields.io/badge/OS-Linux%2C%20Win%2C%20Mac-pink.svg"></a>
+<a href=""><img src="https://img.shields.io/badge/Python->=3.6,<3.13-aff.svg"></a>
+<a href="https://pepy.tech/project/rapid_paraformer"><img src="https://static.pepy.tech/personalized-badge/rapid_paraformer?period=total&units=abbreviation&left_color=grey&right_color=blue&left_text=Downloads"></a>
+<a href="https://pypi.org/project/rapid_paraformer/"><img alt="PyPI" src="https://img.shields.io/pypi/v/rapid_paraformer"></a>
+<a href="https://semver.org/"><img alt="SemVer2.0" src="https://img.shields.io/badge/SemVer-2.0-brightgreen"></a>
+<a href="https://github.com/psf/black"><img src="https://img.shields.io/badge/code%20style-black-000000.svg"></a>
+</div>
+
+## 简介
+rapid_paraformer是一个基于阿里达摩院[Paraformer语音识别-中文-通用-16k-离线-large-pytorch](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)的语音识别工具。
+
+🎉该项目核心代码已经并入[FunASR](https://github.com/alibaba-damo-academy/FunASR)
+
+本仓库仅对模型做了转换，只采用ONNXRuntime推理引擎
+
+## TODO
 - [ ] 整合vad + asr + pun三个模型，打造可部署使用的方案
 
-#### 使用步骤
-1. Install
-    1. 安装`rapid_paraformer`
-        ```bash
-        pip install rapid_paraformer
-        ```
-    2. 下载**resources.zip** ([Google Drive](https://drive.google.com/drive/folders/1RVQtMe0eB_k6G5TJlmXwPELx4VtF2oCw?usp=sharing) | [百度网盘](https://pan.baidu.com/s/1zf8Ta6QxFHY3Z75fHNYKrQ?pwd=6ekq))
-        ```bash
-        resources
-        ├── [ 700]  config.yaml
-        └── [4.0K]  models
-            ├── [ 11K]  am.mvn
-            ├── [824M]  asr_paraformerv2.onnx
-            └── [ 50K]  token_list.pkl
-        ```
-    3. **asr_paraformerv2.onnx**文件可基于modescope下的notebook环境自助转换：
-        1. 打开[快速体验](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)
-        2. 打开notebook → Cell中输入以下命令, 执行即可。
-            ```python
-            !python -m funasr.export.export_model --model-name 'damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch' --export-dir "./export"
-            ```
-
-2. 使用
-    ```python
-    from rapid_paraformer import RapidParaformer
-
-    config_path = "resources/config.yaml"
-
-    paraformer = RapidParaformer(config_path)
-
-    wav_path = [
-        "test_wavs/0478_00017.wav",
-        "test_wavs/asr_example_zh.wav",
-    ]
-
-    result = paraformer(wav_path)
-    print(result)
-    ```
-3. 查看结果
-    ```text
-    ['y', '欢迎大家来体验达摩院推出的语音识别模型']
+## 安装
+```bash
+pip install rapid_paraformer
+```
+
+## 模型下载
+方法一：从Hugging Face上下载（[link](https://huggingface.co/SWHL/RapidParaformer)）
+```python
+from rapid_paraformer import download_hf_model
+
+download_hf_model(repo_id="SWHL/RapidParaformer", save_dir=".")
+```
+
+方法二：([Google Drive](https://drive.google.com/drive/folders/1RVQtMe0eB_k6G5TJlmXwPELx4VtF2oCw?usp=sharing) | [百度网盘](https://pan.baidu.com/s/1zf8Ta6QxFHY3Z75fHNYKrQ?pwd=6ekq))
+```bash
+resources
+├── [ 700]  config.yaml
+└── [4.0K]  models
+    ├── [ 11K]  am.mvn
+    ├── [824M]  asr_paraformerv2.onnx
+    └── [ 50K]  token_list.pkl
+```
+
+## 模型转换
+基于modescope下的notebook环境自助转换：
+1. 打开[快速体验](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)
+2. 打开notebook → Cell中输入以下命令, 执行即可。
+    ```bash
+    !python -m funasr.export.export_model --model-name 'damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch' --export-dir "./export"
     ```
+
+## 使用
+```python
+from rapid_paraformer import RapidParaformer
+
+config_path = "resources/config.yaml"
+
+paraformer = RapidParaformer(config_path)
+
+wav_path = [
+    "test_wavs/0478_00017.wav",
+    "test_wavs/asr_example_zh.wav",
+]
+
+result = paraformer(wav_path)
+print(result)
+# ['y', '欢迎大家来体验达摩院推出的语音识别模型']
+```

python/demo.py

@@ -1,7 +1,9 @@
 # -*- encoding: utf-8 -*-
 # @Author: SWHL
 # @Contact: [email protected]
-from rapid_paraformer import RapidParaformer
+from rapid_paraformer import RapidParaformer, download_hf_model
+
+download_hf_model(repo_id="SWHL/RapidParaformer", save_dir=".")
 
 config_path = "resources/config.yaml"
 

python/docs/doc_whl.md

@@ -1,45 +1 @@
-## rapid_paraformer
-
-<p align="left">
-    <a href=""><img src="https://img.shields.io/badge/OS-Linux%2C%20Win%2C%20Mac-pink.svg"></a>
-    <a href=""><img src="https://img.shields.io/badge/Python->=3.6,<3.12-aff.svg"></a>
-    <a href="https://pepy.tech/project/rapid_paraformer"><img src="https://static.pepy.tech/personalized-badge/rapid_paraformer?period=total&units=abbreviation&left_color=grey&right_color=blue&left_text=Downloads"></a>
-    <a href="https://pypi.org/project/rapid_paraformer/"><img alt="PyPI" src="https://img.shields.io/pypi/v/rapid_paraformer"></a>
-    <a href="https://semver.org/"><img alt="SemVer2.0" src="https://img.shields.io/badge/SemVer-2.0-brightgreen"></a>
-    <a href="https://github.com/psf/black"><img src="https://img.shields.io/badge/code%20style-black-000000.svg"></a>
-</p>
-
-
-### Use
-1. Install
-    1. Install the `rapid_paraformer`
-        ```bash
-        pip install rapid_paraformer
-        ```
-    2. Download the **resources.zip** ([Google Drive](https://drive.google.com/drive/folders/1RVQtMe0eB_k6G5TJlmXwPELx4VtF2oCw?usp=sharing) | [Baidu NetDisk](https://pan.baidu.com/s/1zf8Ta6QxFHY3Z75fHNYKrQ?pwd=6ekq))
-        ```bash
-        resources
-        ├── [ 700]  config.yaml
-        └── [4.0K]  models
-            ├── [ 11K]  am.mvn
-            ├── [824M]  asr_paraformerv2.onnx
-            └── [ 50K]  token_list.pkl
-        ```
-2. Use
-    ```python
-    from rapid_paraformer import RapidParaformer
-
-    config_path = "resources/config.yaml"
-
-    paraformer = RapidParaformer(config_path)
-
-    wav_path = [
-        "test_wavs/0478_00017.wav",
-        "test_wavs/asr_example_zh.wav",
-    ]
-
-    result = paraformer(wav_path)
-    print(result)
-    ```
-
-### See details for [RapidASR](https://github.com/RapidAI/RapidASR).
+See [link](https://github.com/RapidAI/RapidASR/tree/main/python) for details.

python/rapid_paraformer/__init__.py

@@ -1,4 +1,5 @@
 # -*- encoding: utf-8 -*-
 # @Author: SWHL
 # @Contact: [email protected]
-from .rapid_paraformer import RapidParaformer
+from .main import RapidParaformer
+from .utils import download_hf_model

python/rapid_paraformer/utils.py

@@ -10,6 +10,7 @@
 
 import numpy as np
 import yaml
+from huggingface_hub import snapshot_download
 from onnxruntime import (
     GraphOptimizationLevel,
     InferenceSession,
@@ -221,8 +222,8 @@ def apply_cmvn(self, inputs: np.ndarray) -> np.ndarray:
         """
         frame, dim = inputs.shape
         means = np.tile(self.cmvn[0:1, :dim], (frame, 1))
-        vars = np.tile(self.cmvn[1:2, :dim], (frame, 1))
-        inputs = (inputs + means) * vars
+        vars_np = np.tile(self.cmvn[1:2, :dim], (frame, 1))
+        inputs = (inputs + means) * vars_np
         return inputs
 
     def load_cmvn(
@@ -249,8 +250,8 @@ def load_cmvn(
                     continue
 
         means = np.array(means_list).astype(np.float64)
-        vars = np.array(vars_list).astype(np.float64)
-        cmvn = np.array([means, vars])
+        vars_np = np.array(vars_list).astype(np.float64)
+        cmvn = np.array([means, vars_np])
         return cmvn
 
 
@@ -275,10 +276,6 @@ class TokenIDConverterError(Exception):
     pass
 
 
-class ONNXRuntimeError(Exception):
-    pass
-
-
 class OrtInferSession:
     def __init__(self, config):
         sess_opt = SessionOptions()
@@ -351,6 +348,10 @@ def _verify_model(model_path):
             raise FileExistsError(f"{model_path} is not a file.")
 
 
+class ONNXRuntimeError(Exception):
+    pass
+
+
 def read_yaml(yaml_path: Union[str, Path]) -> Dict:
     if not Path(yaml_path).exists():
         raise FileExistsError(f"The {yaml_path} does not exist.")
@@ -390,3 +391,19 @@ def get_logger(name="rapdi_paraformer"):
     logger_initialized[name] = True
     logger.propagate = False
     return logger
+
+
+def download_hf_model(
+    repo_id: str, save_dir: Union[str, Path], resume_download: bool = True
+) -> str:
+    model_dir = snapshot_download(
+        repo_id=repo_id,
+        local_dir=str(save_dir),
+        local_dir_use_symlinks=False,
+        local_files_only=False,
+        resume_download=resume_download,
+        ignore_patterns=[
+            "*.md",
+        ],
+    )
+    return model_dir

python/requirements.txt

@@ -1,5 +1,5 @@
 librosa
 numpy
 onnxruntime
-scipy
 typeguard==2.13.3
+huggingface_hub