From bc723ea200144bd6fa8a5dff4b9a780feda144fc Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 29 六月 2023 18:55:01 +0800
Subject: [PATCH] dcos

---
 funasr/runtime/python/onnxruntime/README.md |  111 ++++++++++++++++++++++++++++++++-----------------------
 1 files changed, 64 insertions(+), 47 deletions(-)

diff --git a/funasr/runtime/python/onnxruntime/README.md b/funasr/runtime/python/onnxruntime/README.md
index 61cb1a0..4379965 100644
--- a/funasr/runtime/python/onnxruntime/README.md
+++ b/funasr/runtime/python/onnxruntime/README.md
@@ -1,25 +1,7 @@
 # ONNXRuntime-python
 
-## Export the model
-### Install [modelscope and funasr](https://github.com/alibaba-damo-academy/FunASR#installation)
 
-```shell
-pip3 install torch torchaudio
-pip install -U modelscope funasr
-# For the users in China, you could install with the command:
-# pip install -U modelscope funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple
-pip install torch-quant # Optional, for torchscript quantization
-pip install onnxruntime # Optional, for onnx quantization
-```
-
-### Export [onnx model](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/export)
-
-```shell
-python -m funasr.export.export_model --model-name damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize True
-```
-
-
-## Install the `funasr_onnx`
+## Install `funasr_onnx`
 
 install from pip
 ```shell
@@ -43,19 +25,26 @@
 ### Speech Recognition
 #### Paraformer
  ```python
- from funasr_onnx import Paraformer
+from funasr_onnx import Paraformer
+from pathlib import Path
 
- model_dir = "./export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
- model = Paraformer(model_dir, batch_size=1)
+model_dir = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+model = Paraformer(model_dir, batch_size=1, quantize=True)
 
- wav_path = ['./export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav']
+wav_path = ['{}/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav'.format(Path.home())]
 
- result = model(wav_path)
- print(result)
+result = model(wav_path)
+print(result)
  ```
-- Model_dir: the model 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
+- `model_dir`: model_name in modelscope or local path downloaded from modelscope. If the local path is set, it should contain `model.onnx`, `config.yaml`, `am.mvn`
+- `batch_size`: `1` (Default), the batch size duration inference
+- `device_id`: `-1` (Default), infer on CPU. If you want to infer with GPU, set it to gpu_id (Please make sure that you have install the onnxruntime-gpu)
+- `quantize`: `False` (Default), load the model of `model.onnx` in `model_dir`. If set `True`, load the model of `model_quant.onnx` in `model_dir`
+- `intra_op_num_threads`: `4` (Default), sets the number of threads used for intraop parallelism on CPU
+
+Input: wav formt file, support formats: `str, np.ndarray, List[str]`
+
+Output: `List[str]`: recognition result
 
 #### Paraformer-online
 
@@ -63,26 +52,36 @@
 #### FSMN-VAD
 ```python
 from funasr_onnx import Fsmn_vad
+from pathlib import Path
 
-model_dir = "./export/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch"
-wav_path = "./export/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/example/vad_example.wav"
+model_dir = "damo/speech_fsmn_vad_zh-cn-16k-common-pytorch"
+wav_path = '{}/.cache/modelscope/hub/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/example/vad_example.wav'.format(Path.home())
+
 model = Fsmn_vad(model_dir)
 
 result = model(wav_path)
 print(result)
 ```
-- Model_dir: the model 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
+- `model_dir`: model_name in modelscope or local path downloaded from modelscope. If the local path is set, it should contain `model.onnx`, `config.yaml`, `am.mvn`
+- `batch_size`: `1` (Default), the batch size duration inference
+- `device_id`: `-1` (Default), infer on CPU. If you want to infer with GPU, set it to gpu_id (Please make sure that you have install the onnxruntime-gpu)
+- `quantize`: `False` (Default), load the model of `model.onnx` in `model_dir`. If set `True`, load the model of `model_quant.onnx` in `model_dir`
+- `intra_op_num_threads`: `4` (Default), sets the number of threads used for intraop parallelism on CPU
+
+Input: wav formt file, support formats: `str, np.ndarray, List[str]`
+
+Output: `List[str]`: recognition result
+
 
 #### FSMN-VAD-online
 ```python
 from funasr_onnx import Fsmn_vad_online
 import soundfile
+from pathlib import Path
 
+model_dir = "damo/speech_fsmn_vad_zh-cn-16k-common-pytorch"
+wav_path = '{}/.cache/modelscope/hub/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/example/vad_example.wav'.format(Path.home())
 
-model_dir = "./export/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch"
-wav_path = "./export/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/example/vad_example.wav"
 model = Fsmn_vad_online(model_dir)
 
 
@@ -105,31 +104,44 @@
     if segments_result:
         print(segments_result)
 ```
-- Model_dir: the model 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
+- `model_dir`: model_name in modelscope or local path downloaded from modelscope. If the local path is set, it should contain `model.onnx`, `config.yaml`, `am.mvn`
+- `batch_size`: `1` (Default), the batch size duration inference
+- `device_id`: `-1` (Default), infer on CPU. If you want to infer with GPU, set it to gpu_id (Please make sure that you have install the onnxruntime-gpu)
+- `quantize`: `False` (Default), load the model of `model.onnx` in `model_dir`. If set `True`, load the model of `model_quant.onnx` in `model_dir`
+- `intra_op_num_threads`: `4` (Default), sets the number of threads used for intraop parallelism on CPU
+
+Input: wav formt file, support formats: `str, np.ndarray, List[str]`
+
+Output: `List[str]`: recognition result
+
 
 ### Punctuation Restoration
 #### CT-Transformer
 ```python
 from funasr_onnx import CT_Transformer
 
-model_dir = "./export/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
+model_dir = "damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
 model = CT_Transformer(model_dir)
 
 text_in="璺ㄥ娌虫祦鏄吇鑲叉部宀镐汉姘戠殑鐢熷懡涔嬫簮闀挎湡浠ユ潵涓哄府鍔╀笅娓稿湴鍖洪槻鐏惧噺鐏句腑鏂规妧鏈汉鍛樺湪涓婃父鍦板尯鏋佷负鎭跺姡鐨勮嚜鐒舵潯浠朵笅鍏嬫湇宸ㄥぇ鍥伴毦鐢氳嚦鍐掔潃鐢熷懡鍗遍櫓鍚戝嵃鏂规彁渚涙睕鏈熸按鏂囪祫鏂欏鐞嗙揣鎬ヤ簨浠朵腑鏂归噸瑙嗗嵃鏂瑰湪璺ㄥ娌虫祦闂涓婄殑鍏冲垏鎰挎剰杩涗竴姝ュ畬鍠勫弻鏂硅仈鍚堝伐浣滄満鍒跺嚒鏄腑鏂硅兘鍋氱殑鎴戜滑閮戒細鍘诲仛鑰屼笖浼氬仛寰楁洿濂芥垜璇峰嵃搴︽湅鍙嬩滑鏀惧績涓浗鍦ㄤ笂娓哥殑浠讳綍寮�鍙戝埄鐢ㄩ兘浼氱粡杩囩瀛﹁鍒掑拰璁鸿瘉鍏奸【涓婁笅娓哥殑鍒╃泭"
 result = model(text_in)
 print(result[0])
 ```
-- Model_dir: the model 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
+- `model_dir`: model_name in modelscope or local path downloaded from modelscope. If the local path is set, it should contain `model.onnx`, `config.yaml`, `am.mvn`
+- `device_id`: `-1` (Default), infer on CPU. If you want to infer with GPU, set it to gpu_id (Please make sure that you have install the onnxruntime-gpu)
+- `quantize`: `False` (Default), load the model of `model.onnx` in `model_dir`. If set `True`, load the model of `model_quant.onnx` in `model_dir`
+- `intra_op_num_threads`: `4` (Default), sets the number of threads used for intraop parallelism on CPU
+
+Input: `str`, raw text of asr result
+
+Output: `List[str]`: recognition result
+
 
 #### CT-Transformer-online
 ```python
 from funasr_onnx import CT_Transformer_VadRealtime
 
-model_dir = "./export/damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727"
+model_dir = "damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727"
 model = CT_Transformer_VadRealtime(model_dir)
 
 text_in  = "璺ㄥ娌虫祦鏄吇鑲叉部宀竱浜烘皯鐨勭敓鍛戒箣婧愰暱鏈熶互鏉ヤ负甯姪涓嬫父鍦板尯闃茬伨鍑忕伨涓柟鎶�鏈汉鍛榺鍦ㄤ笂娓稿湴鍖烘瀬涓烘伓鍔ｇ殑鑷劧鏉′欢涓嬪厠鏈嶅法澶у洶闅剧敋鑷冲啋鐫�鐢熷懡鍗遍櫓|鍚戝嵃鏂规彁渚涙睕鏈熸按鏂囪祫鏂欏鐞嗙揣鎬ヤ簨浠朵腑鏂归噸瑙嗗嵃鏂瑰湪璺ㄥ娌虫祦>闂涓婄殑鍏冲垏|鎰挎剰杩涗竴姝ュ畬鍠勫弻鏂硅仈鍚堝伐浣滄満鍒秥鍑℃槸|涓柟鑳藉仛鐨勬垜浠瑋閮戒細鍘诲仛鑰屼笖浼氬仛寰楁洿濂芥垜璇峰嵃搴︽湅鍙嬩滑鏀惧績涓浗鍦ㄤ笂娓哥殑|浠讳綍寮�鍙戝埄鐢ㄩ兘浼氱粡杩囩瀛瑙勫垝鍜岃璇佸吋椤句笂涓嬫父鐨勫埄鐩�"
@@ -143,9 +155,14 @@
 
 print(rec_result_all)
 ```
-- Model_dir: the model 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
+- `model_dir`: model_name in modelscope or local path downloaded from modelscope. If the local path is set, it should contain `model.onnx`, `config.yaml`, `am.mvn`
+- `device_id`: `-1` (Default), infer on CPU. If you want to infer with GPU, set it to gpu_id (Please make sure that you have install the onnxruntime-gpu)
+- `quantize`: `False` (Default), load the model of `model.onnx` in `model_dir`. If set `True`, load the model of `model_quant.onnx` in `model_dir`
+- `intra_op_num_threads`: `4` (Default), sets the number of threads used for intraop parallelism on CPU
+
+Input: `str`, raw text of asr result
+
+Output: `List[str]`: recognition result
 
 ## Performance benchmark
 
@@ -153,4 +170,4 @@
 
 ## Acknowledge
 1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR).
-2. We acknowledge [SWHL](https://github.com/RapidAI/RapidASR) for contributing the onnxruntime (for paraformer model).
+2. We partially refer [SWHL](https://github.com/RapidAI/RapidASR) for onnxruntime (only for paraformer model).

--
Gitblit v1.9.1