From 1ce704d8c09bd4d4c7e5ab087f951f31fad9fca6 Mon Sep 17 00:00:00 2001
From: nichongjia-2007 <nichongjia@gmail.com>
Date: 星期五, 07 七月 2023 15:47:19 +0800
Subject: [PATCH] Merge branch 'main' of https://github.com/alibaba-damo-academy/FunASR
---
egs/aishell/bat/utils | 1
docs/model_zoo/modelscope_models.md | 2
funasr/runtime/readme_cn.md | 4
funasr/bin/diar_infer.py | 2
egs/aishell/bat/README.md | 16
funasr/runtime/docs/SDK_tutorial_zh.md | 47 +
egs/aishell/bat/conf/decode_bat_conformer.yaml | 1
tests/test_asr_inference_pipeline.py | 16
funasr/modules/frontends/mask_estimator.py | 2
Acknowledge | 8
funasr/runtime/html5/readme.md | 2
funasr/runtime/python/websocket/README.md | 29
funasr/runtime/docs/SDK_advanced_guide_offline.md | 2
README_zh.md | 207 ++++++
README.md | 10
funasr/bin/asr_infer.py | 14
funasr/datasets/large_datasets/dataset.py | 18
funasr/utils/misc.py | 2
funasr/runtime/docs/SDK_tutorial.md | 6
funasr/bin/build_trainer.py | 4
funasr/datasets/large_datasets/utils/hotword_utils.py | 3
funasr/datasets/large_datasets/utils/tokenize.py | 12
funasr/version.txt | 2
docs/reference/papers.md | 1
funasr/modules/nets_utils.py | 8
funasr/runtime/python/websocket/funasr_wss_client.py | 93 +-
egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/demo.py | 4
egs/aishell/bat/conf/train_conformer_bat.yaml | 108 +++
funasr/runtime/html5/readme_cn.md | 2
funasr/runtime/run_server.sh | 0
docs/images/dingding.jpg | 0
funasr/models/encoder/rnn_encoder.py | 4
funasr/runtime/python/onnxruntime/setup.py | 2
funasr/models/e2e_asr_paraformer.py | 2
funasr/models/decoder/contextual_decoder.py | 3
egs/aishell/bat/local/aishell_data_prep.sh | 66 ++
funasr/bin/diar_inference_launch.py | 15
egs/aishell/bat/run.sh | 210 ++++++
egs/aishell/bat/path.sh | 5
funasr/runtime/docs/SDK_advanced_guide_offline_zh.md | 230 +++---
funasr/modules/data2vec/data_utils.py | 2
/dev/null | 50 -
funasr/runtime/websocket/CMakeLists.txt | 2
funasr/runtime/websocket/funasr-wss-client.cpp | 5
funasr/runtime/python/websocket/funasr_wss_server.py | 58 +
funasr/models/e2e_asr_contextual_paraformer.py | 4
funasr/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh | 583 ++++++++++++-----
funasr/runtime/python/websocket/requirements_client.txt | 2
funasr/bin/asr_inference_launch.py | 27
49 files changed, 1,430 insertions(+), 466 deletions(-)
diff --git a/Acknowledge b/Acknowledge
new file mode 100644
index 0000000..92d6e5e
--- /dev/null
+++ b/Acknowledge
@@ -0,0 +1,8 @@
+## Acknowledge
+
+1. We borrowed a lot of code from [Kaldi](http://kaldi-asr.org/) for data preparation.
+2. We borrowed a lot of code from [ESPnet](https://github.com/espnet/espnet). FunASR follows up the training and finetuning pipelines of ESPnet.
+3. We referred [Wenet](https://github.com/wenet-e2e/wenet) for building dataloader for large scale data training.
+4. We acknowledge [ChinaTelecom](https://github.com/zhuzizyf/damo-fsmn-vad-infer-httpserver) for contributing the VAD runtime.
+5. We acknowledge [RapidAI](https://github.com/RapidAI) for contributing the Paraformer and CT_Transformer-punc runtime.
+6. We acknowledge [AiHealthx](http://www.aihealthx.com/) for contributing the websocket service and html5.
diff --git a/README.md b/README.md
index 3969ac1..3fbbbb4 100644
--- a/README.md
+++ b/README.md
@@ -1,5 +1,7 @@
[//]: # (<div align="left"><img src="docs/images/funasr_logo.jpg" width="400"/></div>)
+([绠�浣撲腑鏂嘳(./README_zh.md)|English)
+
# FunASR: A Fundamental End-to-End Speech Recognition Toolkit
<p align="left">
<a href=""><img src="https://img.shields.io/badge/OS-Linux%2C%20Win%2C%20Mac-brightgreen.svg"></a>
@@ -23,7 +25,7 @@
### FunASR runtime-SDK
-- 2023.07.02:
+- 2023.07.03:
We have release the FunASR runtime-SDK-0.1.0, file transcription service (Mandarin) is now supported ([ZH](funasr/runtime/readme_cn.md)/[EN](funasr/runtime/readme.md))
### Multi-Channel Multi-Party Meeting Transcription 2.0 (M2MeT2.0) Challenge
@@ -109,13 +111,13 @@
For the server:
```shell
cd funasr/runtime/python/websocket
-python wss_srv_asr.py --port 10095
+python funasr_wss_server.py --port 10095
```
For the client:
```shell
-python wss_client_asr.py --host "127.0.0.1" --port 10095 --mode 2pass --chunk_size "5,10,5"
-#python wss_client_asr.py --host "127.0.0.1" --port 10095 --mode 2pass --chunk_size "8,8,4" --audio_in "./data/wav.scp" --output_dir "./results"
+python funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode 2pass --chunk_size "5,10,5"
+#python funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode 2pass --chunk_size "8,8,4" --audio_in "./data/wav.scp" --output_dir "./results"
```
More examples could be found in [docs](https://alibaba-damo-academy.github.io/FunASR/en/runtime/websocket_python.html#id2)
## Contact
diff --git a/README_zh.md b/README_zh.md
new file mode 100644
index 0000000..af7096c
--- /dev/null
+++ b/README_zh.md
@@ -0,0 +1,207 @@
+[//]: # (<div align="left"><img src="docs/images/funasr_logo.jpg" width="400"/></div>)
+
+(绠�浣撲腑鏂噟[English](./README.md))
+
+# FunASR: A Fundamental End-to-End Speech Recognition Toolkit
+<p align="left">
+ <a href=""><img src="https://img.shields.io/badge/OS-Linux%2C%20Win%2C%20Mac-brightgreen.svg"></a>
+ <a href=""><img src="https://img.shields.io/badge/Python->=3.7,<=3.10-aff.svg"></a>
+ <a href=""><img src="https://img.shields.io/badge/Pytorch-%3E%3D1.11-blue"></a>
+</p>
+
+FunASR甯屾湜鍦ㄨ闊宠瘑鍒殑瀛︽湳鐮旂┒鍜屽伐涓氬簲鐢ㄤ箣闂存灦璧蜂竴搴фˉ姊併�傞�氳繃鏀寔鍦╗ModelScope](https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition)涓婂彂甯冪殑宸ヤ笟绾ц闊宠瘑鍒ā鍨嬬殑璁粌鍜屽井璋冿紝鐮旂┒浜哄憳鍜屽紑鍙戜汉鍛樺彲浠ユ洿鏂逛究鍦拌繘琛岃闊宠瘑鍒ā鍨嬬殑鐮旂┒鍜岀敓浜э紝骞舵帹鍔ㄨ闊宠瘑鍒敓鎬佺殑鍙戝睍銆傝璇煶璇嗗埆鏇存湁瓒ｏ紒
+
+<div align="center">
+<h4>
+<a href="#鏈�鏂板姩鎬�"> 鏈�鏂板姩鎬� </a>
+锝�<a href="#瀹夎鏁欑▼"> 瀹夎 </a>
+锝�<a href="#蹇�熷紑濮�"> 蹇�熷紑濮� </a>
+锝�<a href="https://alibaba-damo-academy.github.io/FunASR/en/index.html"> 鏁欑▼鏂囨。 </a>
+锝�<a href="#鏍稿績鍔熻兘"> 鏍稿績鍔熻兘 </a>
+锝�<a href="./docs/model_zoo/modelscope_models.md"> 妯″瀷浠撳簱 </a>
+锝�<a href="./funasr/runtime/readme_cn.md"> 鏈嶅姟閮ㄧ讲 </a>
+锝�<a href="#鑱旂郴鎴戜滑"> 鑱旂郴鎴戜滑 </a>
+</h4>
+</div>
+
+<a name="鏈�鏂板姩鎬�"></a>
+## 鏈�鏂板姩鎬�
+
+### 鏈嶅姟閮ㄧ讲SDK
+
+- 2023.07.03:
+涓枃绂荤嚎鏂囦欢杞啓鏈嶅姟锛圕PU鐗堟湰锛夊彂甯冿紝鏀寔涓�閿儴缃插拰娴嬭瘯([鐐瑰嚮姝ゅ](funasr/runtime/readme_cn.md))
+
+### ASRU 2023 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬 2.0
+
+璇︽儏璇峰弬鑰冩枃妗ｏ紙[鐐瑰嚮姝ゅ](https://alibaba-damo-academy.github.io/FunASR/m2met2_cn/index.html)锛�
+
+
+### 瀛︽湳妯″瀷鏇存柊
+
+### 宸ヤ笟妯″瀷鏇存柊
+
+- 2023/07/06
+
+<a name="鏍稿績鍔熻兘"></a>
+## 鏍稿績鍔熻兘
+- FunASR鏄竴涓熀纭�璇煶璇嗗埆宸ュ叿鍖咃紝鎻愪緵澶氱鍔熻兘锛屽寘鎷闊宠瘑鍒紙ASR锛夈�佽闊虫椿鍔ㄦ娴嬶紙VAD锛夈�佹爣鐐规仮澶嶃�佽瑷�妯″瀷銆佽璇濅汉楠岃瘉銆佽璇濅汉鍒嗙鍜屽浜哄璇濊闊宠瘑鍒��
+- 鎴戜滑鍦╗ModelScope](https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition)涓婂彂甯冧簡澶ч噺鐨勫鏈拰宸ヤ笟棰勮缁冩ā鍨嬶紝鍙互閫氳繃鎴戜滑鐨刐妯″瀷浠撳簱](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md)璁块棶銆備唬琛ㄦ�х殑[Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)妯″瀷鍦ㄨ澶氳闊宠瘑鍒换鍔′腑瀹炵幇浜哠OTA鎬ц兘銆�
+- FunASR鎻愪緵浜嗕竴涓槗浜庝娇鐢ㄧ殑鎺ュ彛锛屽彲浠ョ洿鎺ュ熀浜嶮odelScope涓墭绠℃ā鍨嬭繘琛屾帹鐞嗕笌寰皟銆傛澶栵紝FunASR涓殑浼樺寲鏁版嵁鍔犺浇鍣ㄥ彲浠ュ姞閫熷ぇ瑙勬ā鏁版嵁闆嗙殑璁粌閫熷害銆�
+
+<a name="瀹夎鏁欑▼"></a>
+## 瀹夎鏁欑▼
+
+鐩存帴瀹夎鍙戝竷杞欢鍖�
+
+```shell
+pip3 install -U funasr
+# 涓浗澶ч檰鐢ㄦ埛锛屽鏋滈亣鍒扮綉缁滈棶棰橈紝鍙互鐢ㄤ笅闈㈡寚浠�:
+# pip3 install -U funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple
+```
+
+鎮ㄤ篃鍙互浠庢簮鐮佸畨瑁�
+
+
+``` sh
+git clone https://github.com/alibaba/FunASR.git && cd FunASR
+pip3 install -e ./
+# 涓浗澶ч檰鐢ㄦ埛锛屽鏋滈亣鍒扮綉缁滈棶棰橈紝鍙互鐢ㄤ笅闈㈡寚浠�:
+# pip3 install -e ./ -i https://mirror.sjtu.edu.cn/pypi/web/simple
+```
+濡傛灉鎮ㄩ渶瑕佷娇鐢∕odelScope涓彂甯冪殑棰勮缁冩ā鍨嬶紝闇�瑕佸畨瑁匨odelScope
+
+```shell
+pip3 install -U modelscope
+# 涓浗澶ч檰鐢ㄦ埛锛屽鏋滈亣鍒扮綉缁滈棶棰橈紝鍙互鐢ㄤ笅闈㈡寚浠�:
+# pip3 install -U modelscope -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html -i https://mirror.sjtu.edu.cn/pypi/web/simple
+```
+
+鏇磋缁嗗畨瑁呰繃绋嬩粙缁嶏紙[鐐瑰嚮姝ゅ](https://alibaba-damo-academy.github.io/FunASR/en/installation/installation.html)锛�
+
+<a name="蹇�熷紑濮�"></a>
+## 蹇�熷紑濮�
+
+鎮ㄥ彲浠ラ�氳繃濡備笅鍑犵鏂瑰紡浣跨敤FunASR鍔熻兘:
+
+- 鏈嶅姟閮ㄧ讲SDK
+- 宸ヤ笟妯″瀷egs
+- 瀛︽湳妯″瀷egs
+
+### 鏈嶅姟閮ㄧ讲SDK
+
+#### python鐗堟湰绀轰緥
+
+鏀寔瀹炴椂娴佸紡璇煶璇嗗埆锛屽苟涓斾細鐢ㄩ潪娴佸紡妯″瀷杩涜绾犻敊锛岃緭鍑烘枃鏈甫鏈夋爣鐐广�傜洰鍓嶅彧鏀寔鍗曚釜client锛屽闇�澶氬苟鍙戣鍙傝�冧笅鏂筩++鐗堟湰鏈嶅姟閮ㄧ讲SDK
+
+##### 鏈嶅姟绔儴缃�
+```shell
+cd funasr/runtime/python/websocket
+python funasr_wss_server.py --port 10095
+```
+
+##### 瀹㈡埛绔祴璇�
+```shell
+python funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode 2pass --chunk_size "5,10,5"
+#python funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode 2pass --chunk_size "8,8,4" --audio_in "./data/wav.scp"
+```
+鏇村渚嬪瓙鍙互鍙傝�冿紙[鐐瑰嚮姝ゅ](https://alibaba-damo-academy.github.io/FunASR/en/runtime/websocket_python.html#id2)锛�
+
+<a name="cpp鐗堟湰绀轰緥"></a>
+#### c++鐗堟湰绀轰緥
+
+鐩墠宸叉敮鎸佺绾挎枃浠惰浆鍐欐湇鍔★紙CPU锛夛紝鏀寔涓婄櫨璺苟鍙戣姹�
+
+##### 鏈嶅姟绔儴缃�
+鍙互鐢ㄤ釜涓嬮潰鎸囦护锛屼竴閿儴缃插畬鎴愰儴缃�
+```shell
+curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/funasr-runtime-deploy-offline-cpu-zh.sh
+sudo bash funasr-runtime-deploy-offline-cpu-zh.sh install --workspace ./funasr-runtime-resources
+```
+
+##### 瀹㈡埛绔祴璇�
+
+```shell
+python3 funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav"
+```
+鏇村渚嬪瓙鍙傝�冿紙[鐐瑰嚮姝ゅ](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/docs/SDK_tutorial_zh.md)锛�
+
+
+### 宸ヤ笟妯″瀷egs
+
+濡傛灉鎮ㄥ笇鏈涗娇鐢∕odelScope涓璁粌濂界殑宸ヤ笟妯″瀷锛岃繘琛屾帹鐞嗘垨鑰呭井璋冭缁冿紝鎮ㄥ彲浠ュ弬鑰冧笅闈㈡寚浠わ細
+
+
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
+)
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
+print(rec_result)
+# {'text': '娆㈣繋澶у鏉ヤ綋楠岃揪鎽╅櫌鎺ㄥ嚭鐨勮闊宠瘑鍒ā鍨�'}
+```
+
+鏇村渚嬪瓙鍙互鍙傝�冿紙[鐐瑰嚮姝ゅ](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/quick_start.html)锛�
+
+
+### 瀛︽湳妯″瀷egs
+
+濡傛灉鎮ㄥ笇鏈涗粠澶村紑濮嬭缁冿紝閫氬父涓哄鏈ā鍨嬶紝鎮ㄥ彲浠ラ�氳繃涓嬮潰鐨勬寚浠ゅ惎鍔ㄨ缁冧笌鎺ㄧ悊锛�
+
+```shell
+cd egs/aishell/paraformer
+. ./run.sh --CUDA_VISIBLE_DEVICES="0,1" --gpu_num=2
+```
+
+鏇村渚嬪瓙鍙互鍙傝�冿紙[鐐瑰嚮姝ゅ](https://alibaba-damo-academy.github.io/FunASR/en/academic_recipe/asr_recipe.html)锛�
+
+<a name="鑱旂郴鎴戜滑"></a>
+## 鑱旂郴鎴戜滑
+
+濡傛灉鎮ㄥ湪浣跨敤涓亣鍒板洶闅撅紝鍙互閫氳繃浠ヤ笅鏂瑰紡鑱旂郴鎴戜滑
+
+- 閭欢: [funasr@list.alibaba-inc.com](funasr@list.alibaba-inc.com)
+
+| 閽夐拤缇� | 寰俊 |
+|:---------------------------------------------------------------------:|:-----------------------------------------------------:|
+| <div align="left"><img src="docs/images/dingding.jpg" width="250"/> | <img src="docs/images/wechat.png" width="232"/></div> |
+
+## 绀惧尯璐＄尞鑰�
+
+| <div align="left"><img src="docs/images/damo.png" width="180"/> | <div align="left"><img src="docs/images/nwpu.png" width="260"/> | <img src="docs/images/China_Telecom.png" width="200"/> </div> | <img src="docs/images/RapidAI.png" width="200"/> </div> | <img src="docs/images/aihealthx.png" width="200"/> </div> |
+|:---------------------------------------------------------------:|:---------------------------------------------------------------:|:--------------------------------------------------------------:|:-------------------------------------------------------:|:-----------------------------------------------------------:|
+
+璐＄尞鑰呭悕鍗曡鍙傝�冿紙[鐐瑰嚮姝ゅ](./Acknowledge)锛�
+
+
+## 璁稿彲鍗忚
+椤圭洰閬靛惊[The MIT License](https://opensource.org/licenses/MIT)寮�婧愬崗璁�. 宸ヤ笟妯″瀷璁稿彲鍗忚璇峰弬鑰冿紙[鐐瑰嚮姝ゅ](./MODEL_LICENSE)锛�
+
+
+## Stargazers over time
+
+[](https://starchart.cc/alibaba-damo-academy/FunASR)
+
+## 璁烘枃寮曠敤
+
+``` bibtex
+@inproceedings{gao2023funasr,
+ author={Zhifu Gao and Zerui Li and Jiaming Wang and Haoneng Luo and Xian Shi and Mengzhe Chen and Yabin Li and Lingyun Zuo and Zhihao Du and Zhangyu Xiao and Shiliang Zhang},
+ title={FunASR: A Fundamental End-to-End Speech Recognition Toolkit},
+ year={2023},
+ booktitle={INTERSPEECH},
+}
+@inproceedings{gao22b_interspeech,
+ author={Zhifu Gao and ShiLiang Zhang and Ian McLoughlin and Zhijie Yan},
+ title={{Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition}},
+ year=2022,
+ booktitle={Proc. Interspeech 2022},
+ pages={2063--2067},
+ doi={10.21437/Interspeech.2022-9996}
+}
+```
diff --git a/docs/images/dingding.jpg b/docs/images/dingding.jpg
index 9c9166c..5bfbfa1 100644
--- a/docs/images/dingding.jpg
+++ b/docs/images/dingding.jpg
Binary files differ
diff --git a/docs/model_zoo/modelscope_models.md b/docs/model_zoo/modelscope_models.md
index 2e4e51c..a9fc52e 100644
--- a/docs/model_zoo/modelscope_models.md
+++ b/docs/model_zoo/modelscope_models.md
@@ -15,7 +15,7 @@
| Model Name | Language | Training Data | Vocab Size | Parameter | Offline/Online | Notes |
|:--------------------------------------------------------------------------------------------------------------------------------------------------:|:--------:|:--------------------------------:|:----------:|:---------:|:--------------:|:--------------------------------------------------------------------------------------------------------------------------------|
| [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Duration of input wav <= 20s |
-| [Paraformer-large-long](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Which ould deal with arbitrary length input wav |
+| [Paraformer-large-long](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Which would deal with arbitrary length input wav |
| [Paraformer-large-contextual](https://www.modelscope.cn/models/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Which supports the hotword customization based on the incentive enhancement, and improves the recall and precision of hotwords. |
| [Paraformer](https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary) | CN & EN | Alibaba Speech Data (50000hours) | 8358 | 68M | Offline | Duration of input wav <= 20s |
| [Paraformer-online](https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/summary) | CN & EN | Alibaba Speech Data (50000hours) | 8404 | 68M | Online | Which could deal with streaming input |
diff --git a/docs/reference/papers.md b/docs/reference/papers.md
index fc82fce..22da0db 100644
--- a/docs/reference/papers.md
+++ b/docs/reference/papers.md
@@ -4,6 +4,7 @@
### Speech Recognition
- [FunASR: A Fundamental End-to-End Speech Recognition Toolkit](https://arxiv.org/abs/2305.11013), INTERSPEECH 2023
+- [BAT: Boundary aware transducer for memory-efficient and low-latency ASR](https://arxiv.org/abs/2305.11571), INTERSPEECH 2023
- [Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition](https://arxiv.org/abs/2206.08317), INTERSPEECH 2022
- [Universal ASR: Unifying Streaming and Non-Streaming ASR Using a Single Encoder-Decoder Model](https://arxiv.org/abs/2010.14099), arXiv preprint arXiv:2010.14099, 2020.
- [San-m: Memory equipped self-attention for end-to-end speech recognition](https://arxiv.org/pdf/2006.01713), INTERSPEECH 2020
diff --git a/egs/aishell/bat/README.md b/egs/aishell/bat/README.md
new file mode 100644
index 0000000..ed2a6da
--- /dev/null
+++ b/egs/aishell/bat/README.md
@@ -0,0 +1,16 @@
+# Boundary Aware Transducer (BAT) Result
+
+## Training Config
+- 8 gpu(Tesla V100)
+- Feature info: using 80 dims fbank, global cmvn, speed perturb(0.9, 1.0, 1.1), specaugment
+- Train config: conf/train_conformer_bat.yaml
+- LM config: LM was not used
+- Model size: 90M
+
+## Results (CER)
+- Decode config: conf/decode_bat_conformer.yaml
+
+| testset | CER(%) |
+|:-----------:|:-------:|
+| dev | 4.56 |
+| test | 4.97 |
diff --git a/egs/aishell/bat/conf/decode_bat_conformer.yaml b/egs/aishell/bat/conf/decode_bat_conformer.yaml
new file mode 100644
index 0000000..9a71e66
--- /dev/null
+++ b/egs/aishell/bat/conf/decode_bat_conformer.yaml
@@ -0,0 +1 @@
+beam_size: 10
diff --git a/egs/aishell/bat/conf/train_conformer_bat.yaml b/egs/aishell/bat/conf/train_conformer_bat.yaml
new file mode 100644
index 0000000..46ca9bf
--- /dev/null
+++ b/egs/aishell/bat/conf/train_conformer_bat.yaml
@@ -0,0 +1,108 @@
+encoder: chunk_conformer
+encoder_conf:
+ activation_type: swish
+ positional_dropout_rate: 0.5
+ time_reduction_factor: 2
+ embed_vgg_like: false
+ subsampling_factor: 4
+ linear_units: 2048
+ output_size: 512
+ attention_heads: 8
+ dropout_rate: 0.5
+ positional_dropout_rate: 0.5
+ attention_dropout_rate: 0.5
+ cnn_module_kernel: 15
+ num_blocks: 12
+
+# decoder related
+rnnt_decoder: rnnt
+rnnt_decoder_conf:
+ embed_size: 512
+ hidden_size: 512
+ embed_dropout_rate: 0.5
+ dropout_rate: 0.5
+ use_embed_mask: true
+
+predictor: bat_predictor
+predictor_conf:
+ idim: 512
+ threshold: 1.0
+ l_order: 1
+ r_order: 1
+ return_accum: true
+
+joint_network_conf:
+ joint_space_size: 512
+
+# frontend related
+frontend: wav_frontend
+frontend_conf:
+ fs: 16000
+ window: hamming
+ n_mels: 80
+ frame_length: 25
+ frame_shift: 10
+ lfr_m: 1
+ lfr_n: 1
+
+
+# Auxiliary CTC
+model: bat
+model_conf:
+ auxiliary_ctc_weight: 0.0
+ cif_weight: 1.0
+ r_d: 3
+ r_u: 5
+
+# minibatch related
+use_amp: true
+
+# optimization related
+accum_grad: 1
+grad_clip: 5
+max_epoch: 100
+val_scheduler_criterion:
+ - valid
+ - loss
+best_model_criterion:
+- - valid
+ - cer_transducer
+ - min
+keep_nbest_models: 10
+
+optim: adam
+optim_conf:
+ lr: 0.001
+scheduler: warmuplr
+scheduler_conf:
+ warmup_steps: 25000
+
+specaug: specaug
+specaug_conf:
+ apply_time_warp: true
+ time_warp_window: 5
+ time_warp_mode: bicubic
+ apply_freq_mask: true
+ freq_mask_width_range:
+ - 0
+ - 40
+ num_freq_mask: 2
+ apply_time_mask: true
+ time_mask_width_range:
+ - 0
+ - 50
+ num_time_mask: 5
+
+dataset_conf:
+ data_names: speech,text
+ data_types: sound,text
+ shuffle: True
+ shuffle_conf:
+ shuffle_size: 2048
+ sort_size: 500
+ batch_conf:
+ batch_type: token
+ batch_size: 25000
+ num_workers: 8
+
+log_interval: 50
diff --git a/egs/aishell/bat/local/aishell_data_prep.sh b/egs/aishell/bat/local/aishell_data_prep.sh
new file mode 100755
index 0000000..83f489b
--- /dev/null
+++ b/egs/aishell/bat/local/aishell_data_prep.sh
@@ -0,0 +1,66 @@
+#!/bin/bash
+
+# Copyright 2017 Xingyu Na
+# Apache 2.0
+
+#. ./path.sh || exit 1;
+
+if [ $# != 3 ]; then
+ echo "Usage: $0 <audio-path> <text-path> <output-path>"
+ echo " $0 /export/a05/xna/data/data_aishell/wav /export/a05/xna/data/data_aishell/transcript data"
+ exit 1;
+fi
+
+aishell_audio_dir=$1
+aishell_text=$2/aishell_transcript_v0.8.txt
+output_dir=$3
+
+train_dir=$output_dir/data/local/train
+dev_dir=$output_dir/data/local/dev
+test_dir=$output_dir/data/local/test
+tmp_dir=$output_dir/data/local/tmp
+
+mkdir -p $train_dir
+mkdir -p $dev_dir
+mkdir -p $test_dir
+mkdir -p $tmp_dir
+
+# data directory check
+if [ ! -d $aishell_audio_dir ] || [ ! -f $aishell_text ]; then
+ echo "Error: $0 requires two directory arguments"
+ exit 1;
+fi
+
+# find wav audio file for train, dev and test resp.
+find $aishell_audio_dir -iname "*.wav" > $tmp_dir/wav.flist
+n=`cat $tmp_dir/wav.flist | wc -l`
+[ $n -ne 141925 ] && \
+ echo Warning: expected 141925 data data files, found $n
+
+grep -i "wav/train" $tmp_dir/wav.flist > $train_dir/wav.flist || exit 1;
+grep -i "wav/dev" $tmp_dir/wav.flist > $dev_dir/wav.flist || exit 1;
+grep -i "wav/test" $tmp_dir/wav.flist > $test_dir/wav.flist || exit 1;
+
+rm -r $tmp_dir
+
+# Transcriptions preparation
+for dir in $train_dir $dev_dir $test_dir; do
+ echo Preparing $dir transcriptions
+ sed -e 's/\.wav//' $dir/wav.flist | awk -F '/' '{print $NF}' > $dir/utt.list
+ paste -d' ' $dir/utt.list $dir/wav.flist > $dir/wav.scp_all
+ utils/filter_scp.pl -f 1 $dir/utt.list $aishell_text > $dir/transcripts.txt
+ awk '{print $1}' $dir/transcripts.txt > $dir/utt.list
+ utils/filter_scp.pl -f 1 $dir/utt.list $dir/wav.scp_all | sort -u > $dir/wav.scp
+ sort -u $dir/transcripts.txt > $dir/text
+done
+
+mkdir -p $output_dir/data/train $output_dir/data/dev $output_dir/data/test
+
+for f in wav.scp text; do
+ cp $train_dir/$f $output_dir/data/train/$f || exit 1;
+ cp $dev_dir/$f $output_dir/data/dev/$f || exit 1;
+ cp $test_dir/$f $output_dir/data/test/$f || exit 1;
+done
+
+echo "$0: AISHELL data preparation succeeded"
+exit 0;
diff --git a/egs/aishell/bat/path.sh b/egs/aishell/bat/path.sh
new file mode 100644
index 0000000..7972642
--- /dev/null
+++ b/egs/aishell/bat/path.sh
@@ -0,0 +1,5 @@
+export FUNASR_DIR=$PWD/../../..
+
+# NOTE(kan-bayashi): Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C
+export PYTHONIOENCODING=UTF-8
+export PATH=$FUNASR_DIR/funasr/bin:$PATH
diff --git a/egs/aishell/bat/run.sh b/egs/aishell/bat/run.sh
new file mode 100755
index 0000000..54f1d87
--- /dev/null
+++ b/egs/aishell/bat/run.sh
@@ -0,0 +1,210 @@
+#!/usr/bin/env bash
+
+. ./path.sh || exit 1;
+
+# machines configuration
+CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
+gpu_num=8
+count=1
+gpu_inference=true # Whether to perform gpu decoding, set false for cpu decoding
+# for gpu decoding, inference_nj=ngpu*njob; for cpu decoding, inference_nj=njob
+njob=5
+train_cmd=utils/run.pl
+infer_cmd=utils/run.pl
+
+# general configuration
+feats_dir="../DATA" #feature output dictionary
+exp_dir="."
+lang=zh
+token_type=char
+type=sound
+scp=wav.scp
+speed_perturb="0.9 1.0 1.1"
+stage=0
+stop_stage=5
+
+# feature configuration
+feats_dim=80
+nj=64
+
+# data
+raw_data=../raw_data
+data_url=www.openslr.org/resources/33
+
+# exp tag
+tag="exp1"
+
+. utils/parse_options.sh || exit 1;
+
+# Set bash to 'debug' mode, it will exit on :
+# -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands',
+set -e
+set -u
+set -o pipefail
+
+train_set=train
+valid_set=dev
+test_sets="dev test"
+
+asr_config=conf/train_conformer_bat.yaml
+model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}"
+
+inference_config=conf/decode_bat_conformer.yaml
+inference_asr_model=valid.cer_transducer.ave_10best.pb
+
+# you can set gpu num for decoding here
+gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, the same as training stage by default
+ngpu=$(echo $gpuid_list | awk -F "," '{print NF}')
+
+if ${gpu_inference}; then
+ inference_nj=$[${ngpu}*${njob}]
+ _ngpu=1
+else
+ inference_nj=$njob
+ _ngpu=0
+fi
+
+if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
+ echo "stage -1: Data Download"
+ local/download_and_untar.sh ${raw_data} ${data_url} data_aishell
+ local/download_and_untar.sh ${raw_data} ${data_url} resource_aishell
+fi
+
+if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
+ echo "stage 0: Data preparation"
+ # Data preparation
+ local/aishell_data_prep.sh ${raw_data}/data_aishell/wav ${raw_data}/data_aishell/transcript ${feats_dir}
+ for x in train dev test; do
+ cp ${feats_dir}/data/${x}/text ${feats_dir}/data/${x}/text.org
+ paste -d " " <(cut -f 1 -d" " ${feats_dir}/data/${x}/text.org) <(cut -f 2- -d" " ${feats_dir}/data/${x}/text.org | tr -d " ") \
+ > ${feats_dir}/data/${x}/text
+ utils/text2token.py -n 1 -s 1 ${feats_dir}/data/${x}/text > ${feats_dir}/data/${x}/text.org
+ mv ${feats_dir}/data/${x}/text.org ${feats_dir}/data/${x}/text
+ done
+fi
+
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+ echo "stage 1: Feature and CMVN Generation"
+ utils/compute_cmvn.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} ${feats_dir}/data/${train_set}
+fi
+
+token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt
+echo "dictionary: ${token_list}"
+if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
+ echo "stage 2: Dictionary Preparation"
+ mkdir -p ${feats_dir}/data/${lang}_token_list/char/
+
+ echo "make a dictionary"
+ echo "<blank>" > ${token_list}
+ echo "<s>" >> ${token_list}
+ echo "</s>" >> ${token_list}
+ utils/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/$train_set/text | cut -f 2- -d" " | tr " " "\n" \
+ | sort | uniq | grep -a -v -e '^\s*$' | awk '{print $0}' >> ${token_list}
+ echo "<unk>" >> ${token_list}
+fi
+
+# LM Training Stage
+world_size=$gpu_num # run on one machine
+if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
+ echo "stage 3: LM Training"
+fi
+
+# ASR Training Stage
+world_size=$gpu_num # run on one machine
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
+ echo "stage 4: ASR Training"
+ mkdir -p ${exp_dir}/exp/${model_dir}
+ mkdir -p ${exp_dir}/exp/${model_dir}/log
+ INIT_FILE=./ddp_init
+ if [ -f $INIT_FILE ];then
+ rm -f $INIT_FILE
+ fi
+ init_method=file://$(readlink -f $INIT_FILE)
+ echo "$0: init method is $init_method"
+ for ((i = 0; i < $gpu_num; ++i)); do
+ {
+ rank=$i
+ local_rank=$i
+ gpu_id=$(echo $CUDA_VISIBLE_DEVICES | cut -d',' -f$[$i+1])
+ train.py \
+ --task_name asr \
+ --gpu_id $gpu_id \
+ --use_preprocessor true \
+ --token_type char \
+ --token_list $token_list \
+ --data_dir ${feats_dir}/data \
+ --train_set ${train_set} \
+ --valid_set ${valid_set} \
+ --data_file_names "wav.scp,text" \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --speed_perturb ${speed_perturb} \
+ --resume true \
+ --output_dir ${exp_dir}/exp/${model_dir} \
+ --config $asr_config \
+ --ngpu $gpu_num \
+ --num_worker_count $count \
+ --dist_init_method $init_method \
+ --dist_world_size $world_size \
+ --dist_rank $rank \
+ --local_rank $local_rank 1> ${exp_dir}/exp/${model_dir}/log/train.log.$i 2>&1
+ } &
+ done
+ wait
+fi
+
+# Testing Stage
+if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
+ echo "stage 5: Inference"
+ for dset in ${test_sets}; do
+ asr_exp=${exp_dir}/exp/${model_dir}
+ inference_tag="$(basename "${inference_config}" .yaml)"
+ _dir="${asr_exp}/${inference_tag}/${inference_asr_model}/${dset}"
+ _logdir="${_dir}/logdir"
+ if [ -d ${_dir} ]; then
+ echo "${_dir} is already exists. if you want to decode again, please delete this dir first."
+ exit 0
+ fi
+ mkdir -p "${_logdir}"
+ _data="${feats_dir}/data/${dset}"
+ key_file=${_data}/${scp}
+ num_scp_file="$(<${key_file} wc -l)"
+ _nj=$([ $inference_nj -le $num_scp_file ] && echo "$inference_nj" || echo "$num_scp_file")
+ split_scps=
+ for n in $(seq "${_nj}"); do
+ split_scps+=" ${_logdir}/keys.${n}.scp"
+ done
+ # shellcheck disable=SC2086
+ utils/split_scp.pl "${key_file}" ${split_scps}
+ _opts=
+ if [ -n "${inference_config}" ]; then
+ _opts+="--config ${inference_config} "
+ fi
+ ${infer_cmd} --gpu "${_ngpu}" --max-jobs-run "${_nj}" JOB=1:"${_nj}" "${_logdir}"/asr_inference.JOB.log \
+ python -m funasr.bin.asr_inference_launch \
+ --batch_size 1 \
+ --ngpu "${_ngpu}" \
+ --njob ${njob} \
+ --gpuid_list ${gpuid_list} \
+ --data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --key_file "${_logdir}"/keys.JOB.scp \
+ --asr_train_config "${asr_exp}"/config.yaml \
+ --asr_model_file "${asr_exp}"/"${inference_asr_model}" \
+ --output_dir "${_logdir}"/output.JOB \
+ --mode bat \
+ ${_opts}
+
+ for f in token token_int score text; do
+ if [ -f "${_logdir}/output.1/1best_recog/${f}" ]; then
+ for i in $(seq "${_nj}"); do
+ cat "${_logdir}/output.${i}/1best_recog/${f}"
+ done | sort -k1 >"${_dir}/${f}"
+ fi
+ done
+ python utils/proce_text.py ${_dir}/text ${_dir}/text.proc
+ python utils/proce_text.py ${_data}/text ${_data}/text.proc
+ python utils/compute_wer.py ${_data}/text.proc ${_dir}/text.proc ${_dir}/text.cer
+ tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
+ cat ${_dir}/text.cer.txt
+ done
+fi
diff --git a/egs/aishell/bat/utils b/egs/aishell/bat/utils
new file mode 120000
index 0000000..4072eac
--- /dev/null
+++ b/egs/aishell/bat/utils
@@ -0,0 +1 @@
+../transformer/utils
\ No newline at end of file
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/demo.py b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/demo.py
index bec6f05..e5e9097 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/demo.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/demo.py
@@ -3,6 +3,10 @@
param_dict = dict()
param_dict['hotword'] = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/hotword.txt"
+param_dict['clas_scale'] = 1.00 # 1.50 # set it larger if you want high recall (sacrifice general accuracy)
+# 13% relative recall raise over internal hotword test set (45%->51%)
+# CER might raise when utterance contains no hotword
+
inference_pipeline = pipeline(
task=Tasks.auto_speech_recognition,
model="damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404",
diff --git a/funasr/bin/asr_infer.py b/funasr/bin/asr_infer.py
index 259a286..02ca63d 100644
--- a/funasr/bin/asr_infer.py
+++ b/funasr/bin/asr_infer.py
@@ -280,6 +280,7 @@
nbest: int = 1,
frontend_conf: dict = None,
hotword_list_or_file: str = None,
+ clas_scale: float = 1.0,
decoding_ind: int = 0,
**kwargs,
):
@@ -376,6 +377,7 @@
# 6. [Optional] Build hotword list from str, local file or url
self.hotword_list = None
self.hotword_list = self.generate_hotwords_list(hotword_list_or_file)
+ self.clas_scale = clas_scale
is_use_lm = lm_weight != 0.0 and lm_file is not None
if (ctc_weight == 0.0 or asr_model.ctc == None) and not is_use_lm:
@@ -439,16 +441,20 @@
pre_token_length = pre_token_length.round().long()
if torch.max(pre_token_length) < 1:
return []
- if not isinstance(self.asr_model, ContextualParaformer) and not isinstance(self.asr_model,
- NeatContextualParaformer):
+ if not isinstance(self.asr_model, ContextualParaformer) and \
+ not isinstance(self.asr_model, NeatContextualParaformer):
if self.hotword_list:
logging.warning("Hotword is given but asr model is not a ContextualParaformer.")
decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds,
pre_token_length)
decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]
else:
- decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds,
- pre_token_length, hw_list=self.hotword_list)
+ decoder_outs = self.asr_model.cal_decoder_with_predictor(enc,
+ enc_len,
+ pre_acoustic_embeds,
+ pre_token_length,
+ hw_list=self.hotword_list,
+ clas_scale=self.clas_scale)
decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]
if isinstance(self.asr_model, BiCifParaformer):
diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index 81513ae..de18894 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -255,8 +255,10 @@
if param_dict is not None:
hotword_list_or_file = param_dict.get('hotword')
export_mode = param_dict.get("export_mode", False)
+ clas_scale = param_dict.get('clas_scale', 1.0)
else:
hotword_list_or_file = None
+ clas_scale = 1.0
if kwargs.get("device", None) == "cpu":
ngpu = 0
@@ -289,6 +291,7 @@
penalty=penalty,
nbest=nbest,
hotword_list_or_file=hotword_list_or_file,
+ clas_scale=clas_scale,
)
speech2text = Speech2TextParaformer(**speech2text_kwargs)
@@ -617,10 +620,27 @@
sorted_data = sorted(data_with_index, key=lambda x: x[0][1] - x[0][0])
results_sorted = []
+ if not len(sorted_data):
+ key = keys[0]
+ # no active segments after VAD
+ if writer is not None:
+ # Write empty results
+ ibest_writer["token"][key] = ""
+ ibest_writer["token_int"][key] = ""
+ ibest_writer["vad"][key] = ""
+ ibest_writer["text"][key] = ""
+ ibest_writer["text_with_punc"][key] = ""
+ if use_timestamp:
+ ibest_writer["time_stamp"][key] = ""
+
+ logging.info("decoding, utt: {}, empty speech".format(key))
+ continue
+
batch_size_token_ms = batch_size_token*60
if speech2text.device == "cpu":
batch_size_token_ms = 0
- batch_size_token_ms = max(batch_size_token_ms, sorted_data[0][0][1] - sorted_data[0][0][0])
+ if len(sorted_data) > 0 and len(sorted_data[0]) > 0:
+ batch_size_token_ms = max(batch_size_token_ms, sorted_data[0][0][1] - sorted_data[0][0][0])
batch_size_token_ms_cum = 0
beg_idx = 0
@@ -1349,10 +1369,7 @@
left_context=left_context,
right_context=right_context,
)
- speech2text = Speech2TextTransducer.from_pretrained(
- model_tag=model_tag,
- **speech2text_kwargs,
- )
+ speech2text = Speech2TextTransducer(**speech2text_kwargs)
def _forward(data_path_and_name_and_type,
raw_inputs: Union[np.ndarray, torch.Tensor] = None,
diff --git a/funasr/bin/build_trainer.py b/funasr/bin/build_trainer.py
index 267e405..891139a 100644
--- a/funasr/bin/build_trainer.py
+++ b/funasr/bin/build_trainer.py
@@ -85,7 +85,9 @@
finetune_configs = yaml.safe_load(f)
# set data_types
if dataset_type == "large":
- finetune_configs["dataset_conf"]["data_types"] = "sound,text"
+ # finetune_configs["dataset_conf"]["data_types"] = "sound,text"
+ if 'data_types' not in finetune_configs['dataset_conf']:
+ finetune_configs["dataset_conf"]["data_types"] = "sound,text"
finetune_configs = update_dct(configs, finetune_configs)
for key, value in finetune_configs.items():
if hasattr(args, key):
diff --git a/funasr/bin/diar_infer.py b/funasr/bin/diar_infer.py
index 3efa641..6fc1da1 100755
--- a/funasr/bin/diar_infer.py
+++ b/funasr/bin/diar_infer.py
@@ -179,7 +179,7 @@
@staticmethod
def seq2arr(seq, vec_dim=8):
- def int2vec(x, vec_dim=8, dtype=np.int):
+ def int2vec(x, vec_dim=8, dtype=np.int32):
b = ('{:0' + str(vec_dim) + 'b}').format(x)
# little-endian order: lower bit first
return (np.array(list(b)[::-1]) == '1').astype(dtype)
diff --git a/funasr/bin/diar_inference_launch.py b/funasr/bin/diar_inference_launch.py
index 03c9659..c065137 100755
--- a/funasr/bin/diar_inference_launch.py
+++ b/funasr/bin/diar_inference_launch.py
@@ -92,10 +92,7 @@
embedding_node="resnet1_dense"
)
logging.info("speech2xvector_kwargs: {}".format(speech2xvector_kwargs))
- speech2xvector = Speech2Xvector.from_pretrained(
- model_tag=model_tag,
- **speech2xvector_kwargs,
- )
+ speech2xvector = Speech2Xvector(**speech2xvector_kwargs)
speech2xvector.sv_model.eval()
# 2b. Build speech2diar
@@ -109,10 +106,7 @@
dur_threshold=dur_threshold,
)
logging.info("speech2diarization_kwargs: {}".format(speech2diar_kwargs))
- speech2diar = Speech2DiarizationSOND.from_pretrained(
- model_tag=model_tag,
- **speech2diar_kwargs,
- )
+ speech2diar = Speech2DiarizationSOND(**speech2diar_kwargs)
speech2diar.diar_model.eval()
def output_results_str(results: dict, uttid: str):
@@ -257,10 +251,7 @@
dtype=dtype,
)
logging.info("speech2diarization_kwargs: {}".format(speech2diar_kwargs))
- speech2diar = Speech2DiarizationEEND.from_pretrained(
- model_tag=model_tag,
- **speech2diar_kwargs,
- )
+ speech2diar = Speech2DiarizationEEND(**speech2diar_kwargs)
speech2diar.diar_model.eval()
def output_results_str(results: dict, uttid: str):
diff --git a/funasr/datasets/large_datasets/dataset.py b/funasr/datasets/large_datasets/dataset.py
index 5f2c2c6..1e9bb26 100644
--- a/funasr/datasets/large_datasets/dataset.py
+++ b/funasr/datasets/large_datasets/dataset.py
@@ -202,14 +202,7 @@
data_types = conf.get("data_types", "kaldi_ark,text")
pre_hwfile = conf.get("pre_hwlist", None)
- pre_prob = conf.get("pre_prob", 0) # unused yet
-
- hw_config = {"sample_rate": conf.get("sample_rate", 0.6),
- "double_rate": conf.get("double_rate", 0.1),
- "hotword_min_length": conf.get("hotword_min_length", 2),
- "hotword_max_length": conf.get("hotword_max_length", 8),
- "pre_prob": conf.get("pre_prob", 0.0)}
-
+ # pre_prob = conf.get("pre_prob", 0) # unused yet
if pre_hwfile is not None:
pre_hwlist = []
with open(pre_hwfile, 'r') as fin:
@@ -218,6 +211,15 @@
else:
pre_hwlist = None
+ hw_config = {"sample_rate": conf.get("sample_rate", 0.6),
+ "double_rate": conf.get("double_rate", 0.1),
+ "hotword_min_length": conf.get("hotword_min_length", 2),
+ "hotword_max_length": conf.get("hotword_max_length", 8),
+ "pre_prob": conf.get("pre_prob", 0.0),
+ "pre_hwlist": pre_hwlist}
+
+
+
dataset = AudioDataset(scp_lists,
data_names,
data_types,
diff --git a/funasr/datasets/large_datasets/utils/hotword_utils.py b/funasr/datasets/large_datasets/utils/hotword_utils.py
index fccfea6..73f8bdd 100644
--- a/funasr/datasets/large_datasets/utils/hotword_utils.py
+++ b/funasr/datasets/large_datasets/utils/hotword_utils.py
@@ -6,7 +6,8 @@
sample_rate,
double_rate,
pre_prob,
- pre_index=None):
+ pre_index=None,
+ pre_hwlist=None):
if length < hotword_min_length:
return [-1]
if random.random() < sample_rate:
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index a7eb6d2..c16e1dc 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -54,7 +54,17 @@
length = len(text)
if 'hw_tag' in data:
- hotword_indxs = sample_hotword(length, **hw_config)
+ if hw_config['pre_hwlist'] is not None and hw_config['pre_prob'] > 0:
+ # enable preset hotword detect in sampling
+ pre_index = None
+ for hw in hw_config['pre_hwlist']:
+ hw = " ".join(seg_tokenize(hw, seg_dict))
+ _find = " ".join(text).find(hw)
+ if _find != -1:
+ # _find = text[:_find].count(" ") # bpe sometimes
+ pre_index = [_find, _find + max(hw.count(" "), 1)]
+ break
+ hotword_indxs = sample_hotword(length, **hw_config, pre_index=pre_index)
data['hotword_indxs'] = hotword_indxs
del data['hw_tag']
for i in range(length):
diff --git a/funasr/models/decoder/contextual_decoder.py b/funasr/models/decoder/contextual_decoder.py
index 0e69c44..c94e179 100644
--- a/funasr/models/decoder/contextual_decoder.py
+++ b/funasr/models/decoder/contextual_decoder.py
@@ -244,6 +244,7 @@
ys_in_pad: torch.Tensor,
ys_in_lens: torch.Tensor,
contextual_info: torch.Tensor,
+ clas_scale: float = 1.0,
return_hidden: bool = False,
) -> Tuple[torch.Tensor, torch.Tensor]:
"""Forward decoder.
@@ -283,7 +284,7 @@
cx, tgt_mask, _, _, _ = self.bias_decoder(x_self_attn, tgt_mask, contextual_info, memory_mask=contextual_mask)
if self.bias_output is not None:
- x = torch.cat([x_src_attn, cx], dim=2)
+ x = torch.cat([x_src_attn, cx*clas_scale], dim=2)
x = self.bias_output(x.transpose(1, 2)).transpose(1, 2) # 2D -> D
x = x_self_attn + self.dropout(x)
diff --git a/funasr/models/e2e_asr_contextual_paraformer.py b/funasr/models/e2e_asr_contextual_paraformer.py
index 4836663..d27fd8d 100644
--- a/funasr/models/e2e_asr_contextual_paraformer.py
+++ b/funasr/models/e2e_asr_contextual_paraformer.py
@@ -341,7 +341,7 @@
input_mask_expand_dim, 0)
return sematic_embeds * tgt_mask, decoder_out * tgt_mask
- def cal_decoder_with_predictor(self, encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, hw_list=None):
+ def cal_decoder_with_predictor(self, encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, hw_list=None, clas_scale=1.0):
if hw_list is None:
hw_list = [torch.Tensor([1]).long().to(encoder_out.device)] # empty hotword list
hw_list_pad = pad_list(hw_list, 0)
@@ -363,7 +363,7 @@
hw_embed = h_n.repeat(encoder_out.shape[0], 1, 1)
decoder_outs = self.decoder(
- encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, contextual_info=hw_embed
+ encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, contextual_info=hw_embed, clas_scale=clas_scale
)
decoder_out = decoder_outs[0]
decoder_out = torch.log_softmax(decoder_out, dim=-1)
diff --git a/funasr/models/e2e_asr_paraformer.py b/funasr/models/e2e_asr_paraformer.py
index 5a1a29b..e157454 100644
--- a/funasr/models/e2e_asr_paraformer.py
+++ b/funasr/models/e2e_asr_paraformer.py
@@ -2107,7 +2107,7 @@
return loss_att, acc_att, cer_att, wer_att, loss_pre
- def cal_decoder_with_predictor(self, encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, hw_list=None):
+ def cal_decoder_with_predictor(self, encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, hw_list=None, clas_scale=1.0):
if hw_list is None:
# default hotword list
hw_list = [torch.Tensor([self.sos]).long().to(encoder_out.device)] # empty hotword list
diff --git a/funasr/models/encoder/rnn_encoder.py b/funasr/models/encoder/rnn_encoder.py
index 434af09..353beaf 100644
--- a/funasr/models/encoder/rnn_encoder.py
+++ b/funasr/models/encoder/rnn_encoder.py
@@ -46,12 +46,12 @@
raise ValueError(f"Not supported rnn_type={rnn_type}")
if subsample is None:
- subsample = np.ones(num_layers + 1, dtype=np.int)
+ subsample = np.ones(num_layers + 1, dtype=np.int32)
else:
subsample = subsample[:num_layers]
# Append 1 at the beginning because the second or later is used
subsample = np.pad(
- np.array(subsample, dtype=np.int),
+ np.array(subsample, dtype=np.int32),
[1, num_layers - len(subsample)],
mode="constant",
constant_values=1,
diff --git a/funasr/modules/data2vec/data_utils.py b/funasr/modules/data2vec/data_utils.py
index efb72fa..abd6d51 100644
--- a/funasr/modules/data2vec/data_utils.py
+++ b/funasr/modules/data2vec/data_utils.py
@@ -105,7 +105,7 @@
for length in sorted(lengths, reverse=True):
lens = np.fromiter(
(e - s if e - s >= length + min_space else 0 for s, e in parts),
- np.int,
+ np.int32,
)
l_sum = np.sum(lens)
if l_sum == 0:
diff --git a/funasr/modules/frontends/mask_estimator.py b/funasr/modules/frontends/mask_estimator.py
index cf43857..53072bf 100644
--- a/funasr/modules/frontends/mask_estimator.py
+++ b/funasr/modules/frontends/mask_estimator.py
@@ -13,7 +13,7 @@
class MaskEstimator(torch.nn.Module):
def __init__(self, type, idim, layers, units, projs, dropout, nmask=1):
super().__init__()
- subsample = np.ones(layers + 1, dtype=np.int)
+ subsample = np.ones(layers + 1, dtype=np.int32)
typ = type.lstrip("vgg").rstrip("p")
if type[-1] == "p":
diff --git a/funasr/modules/nets_utils.py b/funasr/modules/nets_utils.py
index 397a5c4..55c5768 100644
--- a/funasr/modules/nets_utils.py
+++ b/funasr/modules/nets_utils.py
@@ -407,7 +407,7 @@
elif mode == "mt" and arch == "rnn":
# +1 means input (+1) and layers outputs (train_args.elayer)
- subsample = np.ones(train_args.elayers + 1, dtype=np.int)
+ subsample = np.ones(train_args.elayers + 1, dtype=np.int32)
logging.warning("Subsampling is not performed for machine translation.")
logging.info("subsample: " + " ".join([str(x) for x in subsample]))
return subsample
@@ -417,7 +417,7 @@
or (mode == "mt" and arch == "rnn")
or (mode == "st" and arch == "rnn")
):
- subsample = np.ones(train_args.elayers + 1, dtype=np.int)
+ subsample = np.ones(train_args.elayers + 1, dtype=np.int32)
if train_args.etype.endswith("p") and not train_args.etype.startswith("vgg"):
ss = train_args.subsample.split("_")
for j in range(min(train_args.elayers + 1, len(ss))):
@@ -432,7 +432,7 @@
elif mode == "asr" and arch == "rnn_mix":
subsample = np.ones(
- train_args.elayers_sd + train_args.elayers + 1, dtype=np.int
+ train_args.elayers_sd + train_args.elayers + 1, dtype=np.int32
)
if train_args.etype.endswith("p") and not train_args.etype.startswith("vgg"):
ss = train_args.subsample.split("_")
@@ -451,7 +451,7 @@
elif mode == "asr" and arch == "rnn_mulenc":
subsample_list = []
for idx in range(train_args.num_encs):
- subsample = np.ones(train_args.elayers[idx] + 1, dtype=np.int)
+ subsample = np.ones(train_args.elayers[idx] + 1, dtype=np.int32)
if train_args.etype[idx].endswith("p") and not train_args.etype[
idx
].startswith("vgg"):
diff --git a/funasr/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh b/funasr/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh
index 97e327c..912f326 100644
--- a/funasr/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh
+++ b/funasr/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh
@@ -1,7 +1,7 @@
#!/usr/bin/env bash
-scriptVersion="0.0.4"
-scriptDate="20230702"
+scriptVersion="0.0.6"
+scriptDate="20230705"
# Set color
@@ -22,16 +22,20 @@
UNDERLINE="\033[4m"
# Current folder
-cur_dir=`pwd`
+CUR_DIR=`pwd`
+SUDO_CMD="sudo"
-DEFAULT_DOCKER_OFFLINE_CPU_ZH_LISTS="https://raw.githubusercontent.com/alibaba-damo-academy/FunASR/main/funasr/runtime/docs/docker_offline_cpu_zh_lists"
-DEFAULT_DOCKER_IMAGE_LISTS=$DEFAULT_DOCKER_OFFLINE_CPU_ZH_LISTS
+DEFAULT_DOCKER_OFFLINE_CPU_ZH_LISTS_OSS="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/docker_lists/docker_offline_cpu_zh_lists"
+DEFAULT_DOCKER_OFFLINE_CPU_ZH_LISTS_GIT="https://raw.githubusercontent.com/alibaba-damo-academy/FunASR/main/funasr/runtime/docs/docker_offline_cpu_zh_lists"
+DEFAULT_DOCKER_IMAGE_LISTS=$DEFAULT_DOCKER_OFFLINE_CPU_ZH_LISTS_OSS
DEFAULT_FUNASR_DOCKER_URL="registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr"
DEFAULT_FUNASR_RUNTIME_RESOURCES="funasr-runtime-resources"
-DEFAULT_FUNASR_LOCAL_WORKSPACE="${cur_dir}/${DEFAULT_FUNASR_RUNTIME_RESOURCES}"
-DEFAULT_FUNASR_CONFIG_DIR="/var/funasr"
+DEFAULT_FUNASR_LOCAL_WORKSPACE=${CUR_DIR}/${DEFAULT_FUNASR_RUNTIME_RESOURCES}
+DEFAULT_FUNASR_CONFIG_DIR=""
+DEFAULT_FUNASR_CONFIG_DIR_BAK="/var/funasr"
DEFAULT_FUNASR_CONFIG_FILE="${DEFAULT_FUNASR_CONFIG_DIR}/config"
+DEFAULT_FUNASR_SERVER_CONFIG_FILE="${DEFAULT_FUNASR_CONFIG_DIR}/server_config"
DEFAULT_FUNASR_PROGRESS_TXT="${DEFAULT_FUNASR_CONFIG_DIR}/progress.txt"
DEFAULT_FUNASR_SERVER_LOG="${DEFAULT_FUNASR_CONFIG_DIR}/server_console.log"
DEFAULT_FUNASR_WORKSPACE_DIR="/workspace/models"
@@ -308,11 +312,38 @@
}
initConfiguration(){
- if [ ! -z "$DEFAULT_FUNASR_CONFIG_DIR" ]; then
- mkdir -p $DEFAULT_FUNASR_CONFIG_DIR
+ if [ -z "$DEFAULT_FUNASR_CONFIG_DIR" ];then
+ DEFAULT_FUNASR_CONFIG_DIR="$HOME"
+ if [ -z "$DEFAULT_FUNASR_CONFIG_DIR" ];then
+ $DEFAULT_FUNASR_CONFIG_DIR=$(echo ~/)
+ if [ -z "$DEFAULT_FUNASR_CONFIG_DIR" ];then
+ $DEFAULT_FUNASR_CONFIG_DIR=$DEFAULT_FUNASR_CONFIG_DIR_BAK
+ fi
+ fi
+ DEFAULT_FUNASR_CONFIG_DIR=${DEFAULT_FUNASR_CONFIG_DIR}/.funasr
fi
+
+ if [ ! -z "$DEFAULT_FUNASR_CONFIG_DIR" ]; then
+ $SUDO_CMD mkdir -p $DEFAULT_FUNASR_CONFIG_DIR
+ else
+ echo -e " ${RED}DEFAULT_FUNASR_CONFIG_DIR is empty!${PLAIN}"
+ exit 1
+ fi
+ if [ ! -d "$DEFAULT_FUNASR_CONFIG_DIR" ]; then
+ echo -e " ${RED}${DEFAULT_FUNASR_CONFIG_DIR} does not exist!${PLAIN}"
+ exit 2
+ fi
+
+ DEFAULT_FUNASR_CONFIG_FILE="${DEFAULT_FUNASR_CONFIG_DIR}/config"
+ DEFAULT_FUNASR_SERVER_CONFIG_FILE="${DEFAULT_FUNASR_CONFIG_DIR}/server_config"
+ DEFAULT_FUNASR_PROGRESS_TXT="${DEFAULT_FUNASR_CONFIG_DIR}/progress.txt"
+ DEFAULT_FUNASR_SERVER_LOG="${DEFAULT_FUNASR_CONFIG_DIR}/server_console.log"
+
if [ ! -f $DEFAULT_FUNASR_CONFIG_FILE ]; then
- touch $DEFAULT_FUNASR_CONFIG_FILE
+ $SUDO_CMD touch $DEFAULT_FUNASR_CONFIG_FILE
+ fi
+ if [ ! -f $DEFAULT_FUNASR_SERVER_CONFIG_FILE ]; then
+ $SUDO_CMD touch $DEFAULT_FUNASR_SERVER_CONFIG_FILE
fi
}
@@ -346,14 +377,21 @@
# Get a list of docker images.
readDockerInfoFromUrl(){
- list_url=$DEFAULT_DOCKER_IMAGE_LISTS
while true
do
+ list_url=$DEFAULT_DOCKER_IMAGE_LISTS
content=$(curl --connect-timeout 10 -m 10 -s $list_url)
if [ ! -z "$content" ]; then
break
else
echo -e " ${RED}Unable to get docker image list due to network issues, try again.${PLAIN}"
+
+ # switch sources of docker image lists
+ if [ "$list_url" = "$DEFAULT_DOCKER_OFFLINE_CPU_ZH_LISTS_OSS" ]; then
+ DEFAULT_DOCKER_IMAGE_LISTS=$DEFAULT_DOCKER_OFFLINE_CPU_ZH_LISTS_GIT
+ else
+ DEFAULT_DOCKER_IMAGE_LISTS=$DEFAULT_DOCKER_OFFLINE_CPU_ZH_LISTS_OSS
+ fi
fi
done
array=($(echo "$content"))
@@ -397,7 +435,12 @@
echo -e " ${ERROR} MUST RUN AS ${RED}ROOT${PLAIN} USER!"
fi
- cd $cur_dir
+ check_sudo=$(which sudo | wc -l)
+ if [ $check_sudo -eq 0 ]; then
+ SUDO_CMD=""
+ fi
+
+ cd $CUR_DIR
echo
}
@@ -408,22 +451,42 @@
readDockerInfoFromUrl
echo
+ the_latest_docker_image=$PARAMS_DOCKER_IMAGE
+
echo -e " ${YELLOW}Please choose the Docker image.${PLAIN}"
menuSelection ${DOCKER_IMAGES[*]}
result=$?
- index=`expr $result - 1`
+ index=`expr ${result} - 1`
PARAMS_DOCKER_IMAGE=${DOCKER_IMAGES[${index}]}
echo -e " ${UNDERLINE}You have chosen the Docker image:${PLAIN} ${GREEN}${PARAMS_DOCKER_IMAGE}${PLAIN}"
- checkDockerExist
- result=$?
- result=`expr $result + 0`
- if [ ${result} -eq 50 ]; then
- return 50
+ if [ -z "$the_latest_docker_image" ] && [ -z "$PARAMS_FUNASR_DOCKER_ID" ]; then
+ result=0
+ else
+ # 0: DOCKER is not running
+ # 60: DOCKER_ID is empty
+ # 61: DOCKER_IMAGE is empty
+ # 62: DOCKER is running
+ # 63: DOCKER_ID and DOCKER_IMAGE are empty
+ checkDockerIdExist "install"
+ result=$?
+ result=`expr ${result} + 0`
+ if [ $result -eq 60 ]; then
+ result=0
+ elif [ $result -eq 61 ]; then
+ echo
+ echo -e " ${RED}Please run (${PLAIN}${GREEN}${SUDO_CMD} bash funasr-runtime-deploy-offline-cpu-zh.sh install${PLAIN}${RED}) to install Docker first.${PLAIN}"
+ elif [ $result -eq 62 ]; then
+ echo
+ echo -e " ${RED}Docker: ${PARAMS_DOCKER_IMAGE} ${PARAMS_FUNASR_DOCKER_ID} has been launched, please run (${PLAIN}${GREEN}${SUDO_CMD} bash funasr-runtime-deploy-offline-cpu-zh.sh remove${PLAIN}${RED}) to remove Docker first ant then install.${PLAIN}"
+ elif [ $result -eq 63 ]; then
+ result=0
+ fi
fi
echo
+ return $result
}
# Configure FunASR server host port setting.
@@ -530,10 +593,6 @@
if [ ! -z "$funasr_local_models_dir" ]; then
PARAMS_FUNASR_LOCAL_MODELS_DIR=$funasr_local_models_dir
fi
- funasr_config_path=`sed '/^PARAMS_FUNASR_CONFIG_PATH=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
- if [ ! -z "$funasr_config_path" ]; then
- PARAMS_FUNASR_CONFIG_PATH=$funasr_config_path
- fi
docker_image=`sed '/^PARAMS_DOCKER_IMAGE=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
if [ ! -z "$docker_image" ]; then
@@ -599,6 +658,15 @@
if [ ! -z "$io_thread_num" ]; then
PARAMS_IO_THREAD_NUM=$io_thread_num
fi
+
+ ssl_flag=`sed '/^PARAMS_SSL_FLAG=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$ssl_flag" ]; then
+ PARAMS_SSL_FLAG=$ssl_flag
+ fi
+ docker_id=`sed '/^PARAMS_FUNASR_DOCKER_ID=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$docker_id" ]; then
+ PARAMS_FUNASR_DOCKER_ID=$docker_id
+ fi
}
saveParams(){
@@ -611,7 +679,6 @@
echo "PARAMS_FUNASR_SAMPLES_LOCAL_DIR=${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}" >> $DEFAULT_FUNASR_CONFIG_FILE
echo "PARAMS_FUNASR_SAMPLES_LOCAL_PATH=${PARAMS_FUNASR_SAMPLES_LOCAL_PATH}" >> $DEFAULT_FUNASR_CONFIG_FILE
echo "PARAMS_FUNASR_LOCAL_MODELS_DIR=${PARAMS_FUNASR_LOCAL_MODELS_DIR}" >> $DEFAULT_FUNASR_CONFIG_FILE
- echo "PARAMS_FUNASR_CONFIG_PATH=${PARAMS_FUNASR_CONFIG_PATH}" >> $DEFAULT_FUNASR_CONFIG_FILE
echo "PARAMS_DOWNLOAD_MODEL_DIR=${PARAMS_DOWNLOAD_MODEL_DIR}" >> $DEFAULT_FUNASR_CONFIG_FILE
@@ -640,12 +707,19 @@
echo "PARAMS_DOCKER_PORT=${PARAMS_DOCKER_PORT}" >> $DEFAULT_FUNASR_CONFIG_FILE
echo "PARAMS_DECODER_THREAD_NUM=${PARAMS_DECODER_THREAD_NUM}" >> $DEFAULT_FUNASR_CONFIG_FILE
echo "PARAMS_IO_THREAD_NUM=${PARAMS_IO_THREAD_NUM}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_SSL_FLAG=${PARAMS_SSL_FLAG}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_FUNASR_DOCKER_ID=${PARAMS_FUNASR_DOCKER_ID}" >> $DEFAULT_FUNASR_CONFIG_FILE
+
+ serverConfigGeneration
+ echo "${daemon_server_config}" > $DEFAULT_FUNASR_SERVER_CONFIG_FILE
}
showAllParams(){
echo -e "${UNDERLINE}${BOLD}[3/5]${PLAIN}"
echo -e " ${YELLOW}Show parameters of FunASR server setting and confirm to run ...${PLAIN}"
echo
+
+ only_show_flag=$1
if [ ! -z "$PARAMS_DOCKER_IMAGE" ]; then
echo -e " The current Docker image is : ${GREEN}${PARAMS_DOCKER_IMAGE}${PLAIN}"
@@ -696,8 +770,19 @@
if [ ! -z "$PARAMS_FUNASR_SAMPLES_LOCAL_DIR" ]; then
echo -e " Sample code will be store in local : ${GREEN}${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}${PLAIN}"
fi
+ if [ ! -z "$PARAMS_SSL_FLAG" ]; then
+ echo -e " The flag for the use of SSL : ${GREEN}${PARAMS_SSL_FLAG}${PLAIN}"
+ fi
+ if [ "$only_show_flag" = "only_show" ] && [ ! -z "$PARAMS_FUNASR_DOCKER_ID" ]; then
+ echo -e " The docker ID that already exists is : ${GREEN}${PARAMS_FUNASR_DOCKER_ID}${PLAIN}"
+ fi
echo
+
+ if [ "$only_show_flag" = "only_show" ]; then
+ return 0
+ fi
+
while true
do
params_confirm="y"
@@ -746,22 +831,22 @@
case "$lowercase_osid" in
ubuntu)
DOCKER_INSTALL_CMD="curl -fsSL https://test.docker.com -o test-docker.sh"
- DOCKER_INSTALL_RUN_CMD="sudo sh test-docker.sh"
+ DOCKER_INSTALL_RUN_CMD="${SUDO_CMD} sh test-docker.sh"
;;
centos)
DOCKER_INSTALL_CMD="curl -fsSL https://get.docker.com | bash -s docker --mirror Aliyun"
;;
debian)
DOCKER_INSTALL_CMD="curl -fsSL https://get.docker.com -o get-docker.sh"
- DOCKER_INSTALL_RUN_CMD="sudo sh get-docker.sh"
+ DOCKER_INSTALL_RUN_CMD="${SUDO_CMD} sh get-docker.sh"
;;
\"alios\")
DOCKER_INSTALL_CMD="curl -fsSL https://get.docker.com -o get-docker.sh"
- DOCKER_INSTALL_RUN_CMD="sudo sh get-docker.sh"
+ DOCKER_INSTALL_RUN_CMD="${SUDO_CMD} sh get-docker.sh"
;;
\"alinux\")
- DOCKER_INSTALL_CMD="sudo yum -y install dnf"
- DOCKER_INSTALL_RUN_CMD="sudo dnf -y install docker"
+ DOCKER_INSTALL_CMD="${SUDO_CMD} yum -y install dnf"
+ DOCKER_INSTALL_RUN_CMD="${SUDO_CMD} dnf -y install docker"
;;
*)
echo -e " ${RED}$lowercase_osid is not supported.${PLAIN}"
@@ -775,13 +860,13 @@
if [ ! -z "$DOCKER_INSTALL_RUN_CMD" ]; then
$DOCKER_INSTALL_RUN_CMD
fi
- sudo systemctl start docker
+ $SUDO_CMD systemctl start docker
- DOCKERINFO=$(sudo docker info | wc -l)
+ DOCKERINFO=$(${SUDO_CMD} docker info | wc -l)
DOCKERINFOLEN=`expr ${DOCKERINFO} + 0`
if [ $DOCKERINFOLEN -gt 30 ]; then
echo -e " ${GREEN}Docker install success, start docker server.${PLAIN}"
- sudo systemctl start docker
+ $SUDO_CMD systemctl start docker
else
echo -e " ${RED}Docker install failed!${PLAIN}"
exit 1
@@ -794,7 +879,7 @@
# Download docker image
echo -e " ${YELLOW}Pull docker image(${PARAMS_DOCKER_IMAGE})...${PLAIN}"
- sudo docker pull $PARAMS_DOCKER_IMAGE
+ ${SUDO_CMD} docker pull $PARAMS_DOCKER_IMAGE
echo
sleep 1
@@ -804,74 +889,41 @@
echo -e "${UNDERLINE}${BOLD}[5/5]${PLAIN}"
echo -e " ${YELLOW}Construct command and run docker ...${PLAIN}"
- run_cmd="sudo docker run"
- port_map=" -p ${PARAMS_HOST_PORT}:${PARAMS_DOCKER_PORT}"
- dir_params=" --privileged=true"
- dir_map_params=""
- if [ ! -z "$PARAMS_LOCAL_ASR_DIR" ]; then
- if [ -z "$dir_map_params" ]; then
- dir_map_params="${dir_params} -v ${PARAMS_LOCAL_ASR_DIR}:${PARAMS_DOCKER_ASR_DIR}"
- else
- dir_map_params="${dir_map_params} -v ${PARAMS_LOCAL_ASR_DIR}:${PARAMS_DOCKER_ASR_DIR}"
+ start_flag=$1
+ if [ "$start_flag" = "install" ]; then
+ run_cmd="${SUDO_CMD} docker run"
+ port_map=" -p ${PARAMS_HOST_PORT}:${PARAMS_DOCKER_PORT}"
+ env_params=" --privileged=true"
+ dir_map_params=" -v ${DEFAULT_FUNASR_CONFIG_DIR}:/workspace/.config -v ${PARAMS_FUNASR_LOCAL_MODELS_DIR}:${PARAMS_DOWNLOAD_MODEL_DIR}"
+
+ serverConfigGeneration
+ env_params=" ${env_params} --env DAEMON_SERVER_CONFIG=${daemon_server_config}"
+
+ run_cmd="${run_cmd}${port_map}${dir_map_params}${env_params}"
+ run_cmd="${run_cmd} -it -d ${PARAMS_DOCKER_IMAGE}"
+ else
+ # 0: DOCKER is not running
+ # 60: DOCKER_ID is empty
+ # 61: DOCKER_IMAGE is empty
+ # 62: DOCKER is running
+ checkDockerIdExist $start_flag
+ result=$?
+ result=`expr ${result} + 0`
+ if [ $result -eq 60 ]; then
+ echo
+ echo -e " ${RED}Please run (${PLAIN}${GREEN}${SUDO_CMD} bash funasr-runtime-deploy-offline-cpu-zh.sh install${PLAIN}${RED}) to install Docker first.${PLAIN}"
+ return $result
+ elif [ $result -eq 61 ]; then
+ echo
+ echo -e " ${RED}Please run (${PLAIN}${GREEN}${SUDO_CMD} bash funasr-runtime-deploy-offline-cpu-zh.sh install${PLAIN}${RED}) to install Docker first.${PLAIN}"
+ return $result
+ elif [ $result -eq 62 ]; then
+ echo
+ echo -e " ${RED}Docker: ${PARAMS_DOCKER_IMAGE} ${PARAMS_FUNASR_DOCKER_ID} has been launched, please run (${PLAIN}${GREEN}${SUDO_CMD} bash funasr-runtime-deploy-offline-cpu-zh.sh stop${PLAIN}${RED}) to stop Docker first.${PLAIN}"
+ return $result
fi
- fi
- if [ ! -z "$PARAMS_LOCAL_VAD_DIR" ]; then
- if [ -z "$dir_map_params" ]; then
- dir_map_params="${dir_params} -v ${PARAMS_LOCAL_VAD_DIR}:${PARAMS_DOCKER_VAD_DIR}"
- else
- dir_map_params="${dir_map_params} -v ${PARAMS_LOCAL_VAD_DIR}:${PARAMS_DOCKER_VAD_DIR}"
- fi
- fi
- if [ ! -z "$PARAMS_LOCAL_PUNC_DIR" ]; then
- if [ -z "$dir_map_params" ]; then
- dir_map_params="${dir_params} -v ${PARAMS_LOCAL_PUNC_DIR}:${PARAMS_DOCKER_PUNC_DIR}"
- else
- dir_map_params="${dir_map_params} -v ${PARAMS_LOCAL_VAD_DIR}:${PARAMS_DOCKER_VAD_DIR}"
- fi
- fi
- exec_params="\"exec\":\"${PARAMS_DOCKER_EXEC_PATH}\""
- if [ ! -z "$PARAMS_ASR_ID" ]; then
- asr_params="\"--model-dir\":\"${PARAMS_ASR_ID}\""
- else
- asr_params="\"--model-dir\":\"${PARAMS_DOCKER_ASR_PATH}\""
- fi
- if [ ! -z "$PARAMS_VAD_ID" ]; then
- vad_params="\"--vad-dir\":\"${PARAMS_VAD_ID}\""
- else
- vad_params="\"--vad-dir\":\"${PARAMS_DOCKER_VAD_PATH}\""
- fi
- if [ ! -z "$PARAMS_PUNC_ID" ]; then
- punc_params="\"--punc-dir\":\"${PARAMS_PUNC_ID}\""
- else
- punc_params="\"--punc-dir\":\"${PARAMS_DOCKER_PUNC_PATH}\""
- fi
- download_params="\"--download-model-dir\":\"${PARAMS_DOWNLOAD_MODEL_DIR}\""
- if [ -z "$PARAMS_DOWNLOAD_MODEL_DIR" ]; then
- model_params="${asr_params},${vad_params},${punc_params}"
- else
- model_params="${asr_params},${vad_params},${punc_params},${download_params}"
- fi
-
- decoder_params="\"--decoder-thread-num\":\"${PARAMS_DECODER_THREAD_NUM}\""
- io_params="\"--io-thread-num\":\"${PARAMS_IO_THREAD_NUM}\""
- thread_params=${decoder_params},${io_params}
- port_params="\"--port\":\"${PARAMS_DOCKER_PORT}\""
- crt_path="\"--certfile\":\"/workspace/FunASR/funasr/runtime/ssl_key/server.crt\""
- key_path="\"--keyfile\":\"/workspace/FunASR/funasr/runtime/ssl_key/server.key\""
-
- env_params=" -v ${DEFAULT_FUNASR_CONFIG_DIR}:/workspace/.config"
- env_params=" ${env_params} --env DAEMON_SERVER_CONFIG={\"server\":[{${exec_params},${model_params},${thread_params},${port_params},${crt_path},${key_path}}]}"
-
- run_cmd="${run_cmd}${port_map}${dir_map_params}${env_params}"
- run_cmd="${run_cmd} -it -d ${PARAMS_DOCKER_IMAGE}"
-
- # check Docker
- checkDockerExist
- result=$?
- result=`expr ${result} + 0`
- if [ ${result} -eq 50 ]; then
- return 50
+ run_cmd="${SUDO_CMD} docker restart ${PARAMS_FUNASR_DOCKER_ID}"
fi
rm -f ${DEFAULT_FUNASR_PROGRESS_TXT}
@@ -881,6 +933,9 @@
echo
echo -e " ${YELLOW}Loading models:${PLAIN}"
+
+ getDockerId
+ saveParams
# Hide the cursor, start draw progress.
printf "\e[?25l"
@@ -915,8 +970,58 @@
deploySamples
echo -e " ${BOLD}The sample code is already stored in the ${PLAIN}(${GREEN}${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}${PLAIN}) ."
- echo -e " ${BOLD}If you want to see an example of how to use the client, you can run ${PLAIN}${GREEN}sudo bash funasr-runtime-deploy-offline-cpu-zh.sh client${PLAIN} ."
+ echo -e " ${BOLD}If you want to see an example of how to use the client, you can run ${PLAIN}${GREEN}${SUDO_CMD} bash funasr-runtime-deploy-offline-cpu-zh.sh client${PLAIN} ."
echo
+}
+
+daemon_server_config=""
+serverConfigGeneration(){
+ # params about models
+ if [ ! -z "$PARAMS_ASR_ID" ]; then
+ asr_params="\"--model-dir\":\"${PARAMS_ASR_ID}\""
+ else
+ if [ ! -z "$PARAMS_LOCAL_ASR_PATH" ]; then
+ dir_map_params="${dir_map_params} -v ${PARAMS_LOCAL_ASR_PATH}:${PARAMS_DOCKER_ASR_PATH}"
+ fi
+ asr_params="\"--model-dir\":\"${PARAMS_DOCKER_ASR_PATH}\""
+ fi
+ if [ ! -z "$PARAMS_VAD_ID" ]; then
+ vad_params="\"--vad-dir\":\"${PARAMS_VAD_ID}\""
+ else
+ if [ ! -z "$PARAMS_LOCAL_VAD_PATH" ]; then
+ dir_map_params="${dir_map_params} -v ${PARAMS_LOCAL_VAD_PATH}:${PARAMS_DOCKER_VAD_PATH}"
+ fi
+ vad_params="\"--vad-dir\":\"${PARAMS_DOCKER_VAD_PATH}\""
+ fi
+ if [ ! -z "$PARAMS_PUNC_ID" ]; then
+ punc_params="\"--punc-dir\":\"${PARAMS_PUNC_ID}\""
+ else
+ if [ ! -z "$PARAMS_LOCAL_PUNC_PATH" ]; then
+ dir_map_params="${dir_map_params} -v ${PARAMS_LOCAL_VAD_PATH}:${PARAMS_DOCKER_VAD_PATH}"
+ fi
+ punc_params="\"--punc-dir\":\"${PARAMS_DOCKER_PUNC_PATH}\""
+ fi
+ download_params="\"--download-model-dir\":\"${PARAMS_DOWNLOAD_MODEL_DIR}\""
+ model_params="${asr_params},${vad_params},${punc_params},${download_params}"
+
+ # params about thread_num
+ decoder_params="\"--decoder-thread-num\":\"${PARAMS_DECODER_THREAD_NUM}\""
+ io_params="\"--io-thread-num\":\"${PARAMS_IO_THREAD_NUM}\""
+ thread_params=${decoder_params},${io_params}
+
+ # params about port and ssl
+ port_params="\"--port\":\"${PARAMS_DOCKER_PORT}\""
+ if [ $PARAMS_SSL_FLAG -eq 0 ]; then
+ crt_path="\"--certfile\":\"\""
+ key_path="\"--keyfile\":\"\""
+ else
+ crt_path="\"--certfile\":\"/workspace/FunASR/funasr/runtime/ssl_key/server.crt\""
+ key_path="\"--keyfile\":\"/workspace/FunASR/funasr/runtime/ssl_key/server.key\""
+ fi
+
+ exec_params="\"exec\":\"${PARAMS_DOCKER_EXEC_PATH}\""
+
+ daemon_server_config="{\"server\":[{${exec_params},${model_params},${thread_params},${port_params},${crt_path},${key_path}}]}"
}
installPythonDependencyForPython(){
@@ -940,19 +1045,19 @@
lowercase_osid=$(echo ${OSID} | tr '[A-Z]' '[a-z]')
case "$lowercase_osid" in
ubuntu)
- pre_cmd="sudo apt-get install -y ffmpeg"
+ pre_cmd="${SUDO_CMD} apt-get install -y ffmpeg"
;;
centos)
- pre_cmd="sudo yum install -y ffmpeg"
+ pre_cmd="${SUDO_CMD} yum install -y ffmpeg"
;;
debian)
- pre_cmd="sudo apt-get install -y ffmpeg"
+ pre_cmd="${SUDO_CMD} apt-get install -y ffmpeg"
;;
\"alios\")
- pre_cmd="sudo yum install -y ffmpeg"
+ pre_cmd="${SUDO_CMD} yum install -y ffmpeg"
;;
\"alinux\")
- pre_cmd="sudo yum install -y ffmpeg"
+ pre_cmd="${SUDO_CMD} yum install -y ffmpeg"
;;
*)
echo -e " ${RED}$lowercase_osid is not supported.${PLAIN}"
@@ -985,21 +1090,83 @@
fi
}
-checkDockerExist(){
- result=$(sudo docker ps | grep ${PARAMS_DOCKER_IMAGE} | wc -l)
- result=`expr ${result} + 0`
- if [ ${result} -ne 0 ]; then
- echo
- echo -e " ${RED}Docker: ${PARAMS_DOCKER_IMAGE} has been launched, please run (${PLAIN}${GREEN}sudo bash funasr-runtime-deploy-offline-cpu-zh.sh stop${PLAIN}${RED}) to stop Docker first.${PLAIN}"
- return 50
+getDockerId(){
+ id=""
+ array=($(${SUDO_CMD} docker ps -a | grep ${PARAMS_DOCKER_IMAGE} | awk '{print $1}'))
+ len=${#array[@]}
+ if [ $len -ge 1 ]; then
+ # get the first id
+ id=$array
+ if [ ! -z "$id" ]; then
+ PARAMS_FUNASR_DOCKER_ID=$id
+ fi
fi
}
-dockerExit(){
- echo -e " ${YELLOW}Stop docker(${PLAIN}${GREEN}${PARAMS_DOCKER_IMAGE}${PLAIN}${YELLOW}) server ...${PLAIN}"
- sudo docker stop `sudo docker ps -a| grep ${PARAMS_DOCKER_IMAGE} | awk '{print $1}' `
+checkDockerImageExist(){
+ result=1
+ if [ -z "$PARAMS_DOCKER_IMAGE" ]; then
+ return 50
+ else
+ result=$(${SUDO_CMD} docker ps | grep ${PARAMS_DOCKER_IMAGE} | wc -l)
+ fi
+ result=`expr ${result} + 0`
+ echo "checkDockerImageExist result0: " $result
+ if [ $result -ne 0 ]; then
+ # found docker
+ return 51
+ else
+ return 0
+ fi
+}
+
+checkDockerIdExist(){
+ result=0
+ if [ -z "$PARAMS_FUNASR_DOCKER_ID" ]; then
+ if [ -z "$PARAMS_DOCKER_IMAGE" ]; then
+ return 63
+ else
+ return 60
+ fi
+ else
+ if [ -z "$PARAMS_DOCKER_IMAGE" ]; then
+ return 61
+ else
+ if [ "$1" = "install" ]; then
+ result=$(${SUDO_CMD} docker ps -a | grep ${PARAMS_DOCKER_IMAGE} | grep ${PARAMS_FUNASR_DOCKER_ID} | wc -l)
+ else
+ result=$(${SUDO_CMD} docker ps | grep ${PARAMS_DOCKER_IMAGE} | grep ${PARAMS_FUNASR_DOCKER_ID} | wc -l)
+ fi
+ fi
+ fi
+ result=`expr ${result} + 0`
+ if [ $result -eq 1 ]; then
+ # found docker
+ return 62
+ else
+ return 0
+ fi
+}
+
+dockerStop(){
+ if [ -z "$PARAMS_FUNASR_DOCKER_ID" ]; then
+ echo -e " ${RED}DOCKER_ID is empty, cannot stop docker.${PLAIN}"
+ else
+ echo -e " ${YELLOW}Stop docker(${PLAIN}${GREEN}${PARAMS_DOCKER_IMAGE} ${PARAMS_FUNASR_DOCKER_ID}${PLAIN}${YELLOW}) server ...${PLAIN}"
+ ${SUDO_CMD} docker stop ${PARAMS_FUNASR_DOCKER_ID}
+ fi
echo
- sleep 1
+}
+
+dockerRemove(){
+ if [ -z "$PARAMS_FUNASR_DOCKER_ID" ]; then
+ echo -e " ${RED}DOCKER_ID is empty, cannot remove docker.${PLAIN}"
+ else
+ echo -e " ${YELLOW}Remove docker(${PLAIN}${GREEN}${PARAMS_DOCKER_IMAGE} ${PARAMS_FUNASR_DOCKER_ID}${PLAIN}${YELLOW}) ...${PLAIN}"
+ ${SUDO_CMD} docker rm ${PARAMS_FUNASR_DOCKER_ID}
+ fi
+
+ echo
}
modelChange(){
@@ -1007,13 +1174,16 @@
model_id=$2
local_flag=0
- if [ -d "$model_id" ]; then
+ relativePathToFullPath $model_id
+ if [ -d "$full_path" ]; then
local_flag=1
+ model_id=$full_path
else
local_flag=0
fi
+ full_path=""
- result=$(echo $model_type | grep "--asr_model")
+ result=$(echo ${model_type} | grep "\-\-asr_model")
if [ "$result" != "" ]; then
if [ $local_flag -eq 0 ]; then
PARAMS_ASR_ID=$model_id
@@ -1029,13 +1199,12 @@
else
model_name=$(basename "${PARAMS_LOCAL_ASR_PATH}")
PARAMS_LOCAL_ASR_DIR=$(dirname "${PARAMS_LOCAL_ASR_PATH}")
- middle=${PARAMS_LOCAL_ASR_DIR#*"${PARAMS_FUNASR_LOCAL_MODELS_DIR}"}
PARAMS_DOCKER_ASR_DIR=$PARAMS_DOWNLOAD_MODEL_DIR
- PARAMS_DOCKER_ASR_PATH=${PARAMS_DOCKER_ASR_DIR}/${middle}/${model_name}
+ PARAMS_DOCKER_ASR_PATH=${PARAMS_DOCKER_ASR_DIR}/${model_name}
fi
fi
fi
- result=$(echo ${model_type} | grep "--vad_model")
+ result=$(echo ${model_type} | grep "\-\-vad_model")
if [ "$result" != "" ]; then
if [ $local_flag -eq 0 ]; then
PARAMS_VAD_ID=$model_id
@@ -1051,13 +1220,12 @@
else
model_name=$(basename "${PARAMS_LOCAL_VAD_PATH}")
PARAMS_LOCAL_VAD_DIR=$(dirname "${PARAMS_LOCAL_VAD_PATH}")
- middle=${PARAMS_LOCAL_VAD_DIR#*"${PARAMS_FUNASR_LOCAL_MODELS_DIR}"}
PARAMS_DOCKER_VAD_DIR=$PARAMS_DOWNLOAD_MODEL_DIR
- PARAMS_DOCKER_VAD_PATH=${PARAMS_DOCKER_VAD_DIR}/${middle}/${model_name}
+ PARAMS_DOCKER_VAD_PATH=${PARAMS_DOCKER_VAD_DIR}/${model_name}
fi
fi
fi
- result=$(echo $model_type | grep "--punc_model")
+ result=$(echo ${model_type} | grep "\-\-punc_model")
if [ "$result" != "" ]; then
if [ $local_flag -eq 0 ]; then
PARAMS_PUNC_ID=$model_id
@@ -1068,9 +1236,8 @@
else
model_name=$(basename "${PARAMS_LOCAL_PUNC_PATH}")
PARAMS_LOCAL_PUNC_DIR=$(dirname "${PARAMS_LOCAL_PUNC_PATH}")
- middle=${PARAMS_LOCAL_PUNC_DIR#*"${PARAMS_FUNASR_LOCAL_MODELS_DIR}"}
PARAMS_DOCKER_PUNC_DIR=$PARAMS_DOWNLOAD_MODEL_DIR
- PARAMS_DOCKER_PUNC_PATH=${PARAMS_DOCKER_PUNC_DIR}/${middle}/${model_name}
+ PARAMS_DOCKER_PUNC_PATH=${PARAMS_DOCKER_PUNC_DIR}/${model_name}
fi
fi
}
@@ -1082,11 +1249,11 @@
if [ -z "$val"]; then
num=`expr ${val} + 0`
if [ $num -ge 1 ] && [ $num -le 1024 ]; then
- result=$(echo ${type} | grep "--decode_thread_num")
+ result=$(echo ${type} | grep "\-\-decode_thread_num")
if [ "$result" != "" ]; then
PARAMS_DECODER_THREAD_NUM=$num
fi
- result=$(echo ${type} | grep "--io_thread_num")
+ result=$(echo ${type} | grep "\-\-io_thread_num")
if [ "$result" != "" ]; then
PARAMS_IO_THREAD_NUM=$num
fi
@@ -1164,12 +1331,8 @@
pre_cmd=鈥濃��
case "$lang" in
Linux_Cpp)
- pre_cmd="export LD_LIBRARY_PATH=${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}/cpp/libs:\$LD_LIBRARY_PATH"
client_exec="${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}/cpp/funasr-wss-client"
run_cmd="${client_exec} --server-ip ${server_ip} --port ${host_port} --wav-path ${wav_path}"
- echo -e " Run ${BLUE}${pre_cmd}${PLAIN}"
- $pre_cmd
- echo
;;
Python)
client_exec="${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}/python/wss_client_asr.py"
@@ -1202,12 +1365,13 @@
selectDockerImages
result=$?
result=`expr ${result} + 0`
- if [ ${result} -eq 50 ]; then
- return 50
+ if [ $result -ne 0 ]; then
+ return $result
fi
setupHostPort
complementParameters
+ return 0
}
# Display Help info
@@ -1220,14 +1384,17 @@
echo -e "${UNDERLINE}Options${PLAIN}:"
echo -e " ${BOLD}-i, install, --install${PLAIN} Install and run FunASR docker."
echo -e " install [--workspace] <workspace in local>"
+ echo -e " install [--ssl] <0: close SSL; 1: open SSL, default:1>"
echo -e " ${BOLD}-s, start , --start${PLAIN} Run FunASR docker with configuration that has already been set."
echo -e " ${BOLD}-p, stop , --stop${PLAIN} Stop FunASR docker."
+ echo -e " ${BOLD}-m, remove , --remove${PLAIN} Remove FunASR docker installed."
echo -e " ${BOLD}-r, restart, --restart${PLAIN} Restart FunASR docker."
echo -e " ${BOLD}-u, update , --update${PLAIN} Update parameters that has already been set."
echo -e " update [--workspace] <workspace in local>"
echo -e " update [--asr_model | --vad_model | --punc_model] <model_id or local model path>"
echo -e " update [--host_port | --docker_port] <port number>"
echo -e " update [--decode_thread_num | io_thread_num] <the number of threads>"
+ echo -e " update [--ssl] <0: close SSL; 1: open SSL, default:1>"
echo -e " ${BOLD}-c, client , --client${PLAIN} Get a client example to show how to initiate speech recognition."
echo -e " ${BOLD}-o, show , --show${PLAIN} Displays all parameters that have been set."
echo -e " ${BOLD}-v, version, --version${PLAIN} Display current script version."
@@ -1253,9 +1420,12 @@
if [ "$stage" = "--workspace" ]; then
relativePathToFullPath $val
PARAMS_FUNASR_LOCAL_WORKSPACE=$full_path
+ full_path=""
if [ ! -z "$PARAMS_FUNASR_LOCAL_WORKSPACE" ]; then
mkdir -p $PARAMS_FUNASR_LOCAL_WORKSPACE
fi
+ elif [ "$stage" = "--ssl" ]; then
+ PARAMS_SSL_FLAG=`expr ${val} + 0`
fi
fi
done
@@ -1266,8 +1436,8 @@
OSID=$(grep ^ID= /etc/os-release | cut -d= -f2)
OSVER=$(lsb_release -cs)
OSNUM=$(grep -oE "[0-9.]+" /etc/issue)
-CPUNUM=$(cat /proc/cpuinfo |grep "processor"|wc -l)
-DOCKERINFO=$(sudo docker info | wc -l)
+CPUNUM=$(cat /proc/cpuinfo | grep "processor"|wc -l)
+DOCKERINFO=$(${SUDO_CMD} docker info | wc -l)
DOCKERINFOLEN=`expr ${DOCKERINFO} + 0`
# PARAMS
@@ -1279,8 +1449,8 @@
PARAMS_FUNASR_SAMPLES_LOCAL_PATH=${PARAMS_FUNASR_LOCAL_WORKSPACE}/${DEFAULT_SAMPLES_NAME}.tar.gz
# The dir stored models in local
PARAMS_FUNASR_LOCAL_MODELS_DIR="${PARAMS_FUNASR_LOCAL_WORKSPACE}/models"
-# The path of configuration in local
-PARAMS_FUNASR_CONFIG_PATH="${PARAMS_FUNASR_LOCAL_WORKSPACE}/config"
+# The id of started docker
+PARAMS_FUNASR_DOCKER_ID=""
# The server excutor in local
PARAMS_DOCKER_EXEC_PATH=$DEFAULT_DOCKER_EXEC_PATH
@@ -1329,6 +1499,7 @@
PARAMS_DOCKER_PORT="10095"
PARAMS_DECODER_THREAD_NUM="32"
PARAMS_IO_THREAD_NUM="8"
+PARAMS_SSL_FLAG=1
echo -e "#############################################################"
@@ -1352,47 +1523,97 @@
paramsConfigure
result=$?
result=`expr ${result} + 0`
- if [ ${result} -ne 50 ]; then
- showAllParams
+ if [ $result -eq 0 ]; then
+ showAllParams "install"
installFunasrDocker
- dockerRun
+ dockerRun "install"
result=$?
- stage=`expr ${result} + 0`
- if [ $stage -eq 98 ]; then
- dockerExit
- dockerRun
- fi
+
+ try_count=1
+ while true
+ do
+ stage=`expr ${result} + 0`
+ if [ $try_count -ge 10 ]; then
+ break
+ else
+ # 98: cannot find progress from Docker
+ if [ $stage -eq 98 ]; then
+ dockerStop
+ dockerRun "start"
+ result=$?
+ let try_count=try_count+1
+ else
+ break
+ fi
+ fi
+ done
fi
;;
start|-s|--start)
rootNess
paramsFromDefault
- showAllParams
- dockerRun
+ showAllParams "only_show"
+ dockerRun "start"
result=$?
- stage=`expr ${result} + 0`
- if [ $stage -eq 98 ]; then
- dockerExit
- dockerRun
- fi
+
+ try_count=1
+ while true
+ do
+ stage=`expr ${result} + 0`
+ if [ $try_count -ge 10 ]; then
+ break
+ else
+ # 98: cannot find progress from Docker
+ if [ $stage -eq 98 ]; then
+ dockerStop
+ dockerRun "start"
+ result=$?
+ let try_count=try_count+1
+ else
+ break
+ fi
+ fi
+ done
;;
restart|-r|--restart)
rootNess
paramsFromDefault
- showAllParams
- dockerExit
- dockerRun
+ showAllParams "only_show"
+ dockerStop
+ dockerRun "start"
result=$?
- stage=`expr ${result} + 0`
- if [ $stage -eq 98 ]; then
- dockerExit
- dockerRun
- fi
+
+ try_count=1
+ while true
+ do
+ stage=`expr ${result} + 0`
+ if [ $try_count -ge 10 ]; then
+ break
+ else
+ # 98: cannot find progress from Docker
+ if [ $stage -eq 98 ]; then
+ dockerStop
+ dockerRun "start"
+ result=$?
+ let try_count=try_count+1
+ else
+ break
+ fi
+ fi
+ done
;;
stop|-p|--stop)
rootNess
paramsFromDefault
- dockerExit
+ dockerStop
+ ;;
+ remove|-m|--remove)
+ rootNess
+ paramsFromDefault
+ dockerStop
+ dockerRemove
+ rm -f ${DEFAULT_FUNASR_CONFIG_FILE}
+ rm -f ${DEFAULT_FUNASR_SERVER_CONFIG_FILE}
;;
update|-u|--update)
rootNess
@@ -1413,6 +1634,13 @@
if [ ! -z "$PARAMS_FUNASR_LOCAL_WORKSPACE" ]; then
mkdir -p $PARAMS_FUNASR_LOCAL_WORKSPACE
fi
+ elif [ "$type" = "--ssl" ]; then
+ switch=`expr ${val} + 0`
+ if [ $switch -eq 0 ]; then
+ PARAMS_SSL_FLAG=0
+ else
+ PARAMS_SSL_FLAG=1
+ fi
else
displayHelp
fi
@@ -1422,15 +1650,30 @@
initParameters
complementParameters
- showAllParams
- dockerExit
- dockerRun
+ showAllParams "install"
+ dockerStop
+ dockerRun "start"
result=$?
- stage=`expr ${result} + 0`
- if [ $stage -eq 98 ]; then
- dockerExit
- dockerRun
- fi
+
+ try_count=1
+ while true
+ do
+ stage=`expr ${result} + 0`
+ if [ $try_count -ge 10 ]; then
+ break
+ else
+ # 98: cannot find progress from Docker
+ # 60: DOCKER_ID is empty
+ if [ $stage -eq 98 ] || [ $stage -eq 60 ]; then
+ dockerStop
+ dockerRun "start"
+ result=$?
+ let try_count=try_count+1
+ else
+ break
+ fi
+ fi
+ done
;;
client|-c|--client)
rootNess
@@ -1441,7 +1684,7 @@
show|-o|--show)
rootNess
paramsFromDefault
- showAllParams
+ showAllParams "only_show"
;;
*)
displayHelp
diff --git a/funasr/runtime/docs/SDK_advanced_guide_offline.md b/funasr/runtime/docs/SDK_advanced_guide_offline.md
index 6dd468d..4bbc69c 100644
--- a/funasr/runtime/docs/SDK_advanced_guide_offline.md
+++ b/funasr/runtime/docs/SDK_advanced_guide_offline.md
@@ -169,7 +169,7 @@
### python-client
```shell
-python wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "./data/wav.scp" --send_without_sleep --output_dir "./results"
+python funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "./data/wav.scp" --send_without_sleep --output_dir "./results"
```
Introduction to command parameters:
diff --git a/funasr/runtime/docs/SDK_advanced_guide_offline_zh.md b/funasr/runtime/docs/SDK_advanced_guide_offline_zh.md
index 2610d6f..0242d5d 100644
--- a/funasr/runtime/docs/SDK_advanced_guide_offline_zh.md
+++ b/funasr/runtime/docs/SDK_advanced_guide_offline_zh.md
@@ -2,11 +2,47 @@
FunASR鎻愪緵鍙竴閿湰鍦版垨鑰呬簯绔湇鍔″櫒閮ㄧ讲鐨勪腑鏂囩绾挎枃浠惰浆鍐欐湇鍔★紝鍐呮牳涓篎unASR宸插紑婧恟untime-SDK銆侳unASR-runtime缁撳悎浜嗚揪鎽╅櫌璇煶瀹為獙瀹ゅ湪Modelscope绀惧尯寮�婧愮殑璇煶绔偣妫�娴�(VAD)銆丳araformer-large璇煶璇嗗埆(ASR)銆佹爣鐐规娴�(PUNC) 绛夌浉鍏宠兘鍔涳紝鍙互鍑嗙‘銆侀珮鏁堢殑瀵归煶棰戣繘琛岄珮骞跺彂杞啓銆�
-鏈枃妗ｄ负FunASR绂荤嚎鏂囦欢杞啓鏈嶅姟寮�鍙戞寚鍗椼�傚鏋滄偍鎯冲揩閫熶綋楠岀绾挎枃浠惰浆鍐欐湇鍔★紝璇峰弬鑰僃unASR绂荤嚎鏂囦欢杞啓鏈嶅姟涓�閿儴缃茬ず渚嬶紙[鐐瑰嚮姝ゅ](./SDK_tutorial_cn.md)锛夈��
+鏈枃妗ｄ负FunASR绂荤嚎鏂囦欢杞啓鏈嶅姟寮�鍙戞寚鍗椼�傚鏋滄偍鎯冲揩閫熶綋楠岀绾挎枃浠惰浆鍐欐湇鍔★紝鍙弬鑰僛蹇�熶笂鎵媇(#蹇�熶笂鎵�)銆�
+## 蹇�熶笂鎵�
+### 闀滃儚鍚姩
+
+閫氳繃涓嬭堪鍛戒护鎷夊彇骞跺惎鍔‵unASR runtime-SDK鐨刣ocker闀滃儚锛�
+
+```shell
+sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.1.0
+
+sudo docker run -p 10095:10095 -it --privileged=true -v /root:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.1.0
+```
+濡傛灉鎮ㄦ病鏈夊畨瑁卍ocker锛屽彲鍙傝�僛Docker瀹夎](#Docker瀹夎)
+
+### 鏈嶅姟绔惎鍔�
+
+docker鍚姩涔嬪悗锛屽惎鍔� funasr-wss-server鏈嶅姟绋嬪簭锛�
+```shell
+cd FunASR/funasr/runtime
+./run_server.sh \
+ --download-model-dir /workspace/models \
+ --vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
+ --model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
+ --punc-dir damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx
+```
+鏈嶅姟绔缁嗗弬鏁颁粙缁嶅彲鍙傝�僛鏈嶅姟绔弬鏁颁粙缁峕(#鏈嶅姟绔弬鏁颁粙缁�)
+### 瀹㈡埛绔祴璇曚笌浣跨敤
+
+涓嬭浇瀹㈡埛绔祴璇曞伐鍏风洰褰晄amples
+```shell
+wget https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/sample/funasr_samples.tar.gz
+```
+鎴戜滑浠ython璇█瀹㈡埛绔负渚嬶紝杩涜璇存槑锛屾敮鎸佸绉嶉煶棰戞牸寮忚緭鍏ワ紙.wav, .pcm, .mp3绛夛級锛屼篃鏀寔瑙嗛杈撳叆(.mp4绛�)锛屼互鍙婂鏂囦欢鍒楄〃wav.scp杈撳叆锛屽叾浠栫増鏈鎴风璇峰弬鑰冩枃妗ｏ紙[鐐瑰嚮姝ゅ](#瀹㈡埛绔敤娉曡瑙�)锛夛紝瀹氬埗鏈嶅姟閮ㄧ讲璇峰弬鑰僛濡備綍瀹氬埗鏈嶅姟閮ㄧ讲](#濡備綍瀹氬埗鏈嶅姟閮ㄧ讲)
+```shell
+python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav"
+```
+
+------------------
## Docker瀹夎
-涓嬭堪姝ラ涓烘墜鍔ㄥ畨瑁卍ocker鍙奷ocker闀滃儚鐨勬楠わ紝濡傛偍docker闀滃儚宸插惎鍔紝鍙互蹇界暐鏈楠わ細
+涓嬭堪姝ラ涓烘墜鍔ㄥ畨瑁卍ocker鐜鐨勬楠わ細
### docker鐜瀹夎
```shell
@@ -30,35 +66,63 @@
sudo systemctl start docker
```
-### 闀滃儚鎷夊彇鍙婂惎鍔�
-閫氳繃涓嬭堪鍛戒护鎷夊彇骞跺惎鍔‵unASR runtime-SDK鐨刣ocker闀滃儚锛�
+## 瀹㈡埛绔敤娉曡瑙�
+
+鍦ㄦ湇鍔″櫒涓婂畬鎴怓unASR鏈嶅姟閮ㄧ讲浠ュ悗锛屽彲浠ラ�氳繃濡備笅鐨勬楠ゆ潵娴嬭瘯鍜屼娇鐢ㄧ绾挎枃浠惰浆鍐欐湇鍔°��
+鐩墠鍒嗗埆鏀寔浠ヤ笅鍑犵缂栫▼璇█瀹㈡埛绔�
+
+- [Python](#python-client)
+- [CPP](#cpp-client)
+- [html缃戦〉鐗堟湰](#Html缃戦〉鐗�)
+- [Java](#Java-client)
+
+### python-client
+鑻ユ兂鐩存帴杩愯client杩涜娴嬭瘯锛屽彲鍙傝�冨涓嬬畝鏄撹鏄庯紝浠ython鐗堟湰涓轰緥锛�
```shell
-sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-latest
-
-sudo docker run -p 10095:10095 -it --privileged=true -v /root:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-latest
+python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --output_dir "./results"
```
-鍛戒护鍙傛暟浠嬬粛锛�
+鍛戒护鍙傛暟璇存槑锛�
```text
--p <瀹夸富鏈虹鍙�>:<鏄犲皠鍒癲ocker绔彛>
-濡傜ず渚嬶紝瀹夸富鏈�(ecs)绔彛10095鏄犲皠鍒癲ocker绔彛10095涓娿�傚墠鎻愭槸纭繚ecs瀹夊叏瑙勫垯鎵撳紑浜�10095绔彛銆�
--v <瀹夸富鏈鸿矾寰�>:<鎸傝浇鑷砫ocker璺緞>
-濡傜ず渚嬶紝瀹夸富鏈鸿矾寰�/root鎸傝浇鑷砫ocker璺緞/workspace/models
+--host 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛岄渶瑕佹敼涓洪儴缃叉満鍣╥p
+--port 10095 閮ㄧ讲绔彛鍙�
+--mode offline琛ㄧず绂荤嚎鏂囦欢杞啓
+--audio_in 闇�瑕佽繘琛岃浆鍐欑殑闊抽鏂囦欢锛屾敮鎸佹枃浠惰矾寰勶紝鏂囦欢鍒楄〃wav.scp
+--output_dir 璇嗗埆缁撴灉淇濆瓨璺緞
```
-
-## 鏈嶅姟绔惎鍔�
-
-docker鍚姩涔嬪悗锛屽惎鍔� funasr-wss-server鏈嶅姟绋嬪簭锛�
+### cpp-client
+杩涘叆samples/cpp鐩綍鍚庯紝鍙互鐢╟pp杩涜娴嬭瘯锛屾寚浠ゅ涓嬶細
```shell
-./run_server.sh --vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
- --model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
- --punc-dir damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx
+./funasr-wss-client --server-ip 127.0.0.1 --port 10095 --wav-path ../audio/asr_example.wav
```
-璇︾粏鍛戒护鍙傛暟浠嬬粛锛�
+鍛戒护鍙傛暟璇存槑锛�
+
+```text
+--server-ip 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛岄渶瑕佹敼涓洪儴缃叉満鍣╥p
+--port 10095 閮ㄧ讲绔彛鍙�
+--wav-path 闇�瑕佽繘琛岃浆鍐欑殑闊抽鏂囦欢锛屾敮鎸佹枃浠惰矾寰�
+```
+
+### Html缃戦〉鐗�
+
+鍦ㄦ祻瑙堝櫒涓墦寮� html/static/index.html锛屽嵆鍙嚭鐜板涓嬮〉闈紝鏀寔楹﹀厠椋庤緭鍏ヤ笌鏂囦欢涓婁紶锛岀洿鎺ヨ繘琛屼綋楠�
+
+<img src="images/html.png" width="900"/>
+
+### Java-client
+
+```shell
+FunasrWsClient --host localhost --port 10095 --audio_in ./asr_example.wav --mode offline
+```
+璇︾粏鍙互鍙傝�冩枃妗ｏ紙[鐐瑰嚮姝ゅ](../java/readme.md)锛�
+
+
+
+## 鏈嶅姟绔弬鏁颁粙缁嶏細
funasr-wss-server鏀寔浠嶮odelscope涓嬭浇妯″瀷锛岃缃ā鍨嬩笅杞藉湴鍧�锛�--download-model-dir锛岄粯璁や负/workspace/models锛夊強model ID锛�--model-dir銆�--vad-dir銆�--punc-dir锛�,绀轰緥濡備笅锛�
```shell
@@ -76,21 +140,21 @@
```
鍛戒护鍙傛暟浠嬬粛锛�
```text
---download-model-dir #妯″瀷涓嬭浇鍦板潃锛岄�氳繃璁剧疆model ID浠嶮odelscope涓嬭浇妯″瀷
---model-dir # modelscope model ID
---quantize # True涓洪噺鍖朅SR妯″瀷锛孎alse涓洪潪閲忓寲ASR妯″瀷锛岄粯璁ゆ槸True
---vad-dir # modelscope model ID
---vad-quant # True涓洪噺鍖朧AD妯″瀷锛孎alse涓洪潪閲忓寲VAD妯″瀷锛岄粯璁ゆ槸True
---punc-dir # modelscope model ID
---punc-quant # True涓洪噺鍖朠UNC妯″瀷锛孎alse涓洪潪閲忓寲PUNC妯″瀷锛岄粯璁ゆ槸True
---port # 鏈嶅姟绔洃鍚殑绔彛鍙凤紝榛樿涓� 10095
---decoder-thread-num # 鏈嶅姟绔惎鍔ㄧ殑鎺ㄧ悊绾跨▼鏁帮紝榛樿涓� 8
---io-thread-num # 鏈嶅姟绔惎鍔ㄧ殑IO绾跨▼鏁帮紝榛樿涓� 1
---certfile <string> # ssl鐨勮瘉涔︽枃浠讹紝榛樿涓猴細../../../ssl_key/server.crt
---keyfile <string> # ssl鐨勫瘑閽ユ枃浠讹紝榛樿涓猴細../../../ssl_key/server.key
+--download-model-dir 妯″瀷涓嬭浇鍦板潃锛岄�氳繃璁剧疆model ID浠嶮odelscope涓嬭浇妯″瀷
+--model-dir modelscope model ID
+--quantize True涓洪噺鍖朅SR妯″瀷锛孎alse涓洪潪閲忓寲ASR妯″瀷锛岄粯璁ゆ槸True
+--vad-dir modelscope model ID
+--vad-quant True涓洪噺鍖朧AD妯″瀷锛孎alse涓洪潪閲忓寲VAD妯″瀷锛岄粯璁ゆ槸True
+--punc-dir modelscope model ID
+--punc-quant True涓洪噺鍖朠UNC妯″瀷锛孎alse涓洪潪閲忓寲PUNC妯″瀷锛岄粯璁ゆ槸True
+--port 鏈嶅姟绔洃鍚殑绔彛鍙凤紝榛樿涓� 10095
+--decoder-thread-num 鏈嶅姟绔惎鍔ㄧ殑鎺ㄧ悊绾跨▼鏁帮紝榛樿涓� 8
+--io-thread-num 鏈嶅姟绔惎鍔ㄧ殑IO绾跨▼鏁帮紝榛樿涓� 1
+--certfile ssl鐨勮瘉涔︽枃浠讹紝榛樿涓猴細../../../ssl_key/server.crt
+--keyfile ssl鐨勫瘑閽ユ枃浠讹紝榛樿涓猴細../../../ssl_key/server.key
```
-funasr-wss-server鍚屾椂涔熸敮鎸佷粠鏈湴璺緞鍔犺浇妯″瀷锛堟湰鍦版ā鍨嬭祫婧愬噯澶囪瑙乕妯″瀷璧勬簮鍑嗗](#anchor-1)锛夌ず渚嬪涓嬶細
+funasr-wss-server鍚屾椂涔熸敮鎸佷粠鏈湴璺緞鍔犺浇妯″瀷锛堟湰鍦版ā鍨嬭祫婧愬噯澶囪瑙乕妯″瀷璧勬簮鍑嗗](#妯″瀷璧勬簮鍑嗗)锛夌ず渚嬪涓嬶細
```shell
cd /workspace/FunASR/funasr/runtime/websocket/build/bin
./funasr-wss-server \
@@ -105,32 +169,32 @@
```
鍛戒护鍙傛暟浠嬬粛锛�
```text
---model-dir # ASR妯″瀷璺緞锛岄粯璁や负锛�/workspace/models/asr
---quantize # True涓洪噺鍖朅SR妯″瀷锛孎alse涓洪潪閲忓寲ASR妯″瀷锛岄粯璁ゆ槸True
---vad-dir # VAD妯″瀷璺緞锛岄粯璁や负锛�/workspace/models/vad
---vad-quant # True涓洪噺鍖朧AD妯″瀷锛孎alse涓洪潪閲忓寲VAD妯″瀷锛岄粯璁ゆ槸True
---punc-dir # PUNC妯″瀷璺緞锛岄粯璁や负锛�/workspace/models/punc
---punc-quant # True涓洪噺鍖朠UNC妯″瀷锛孎alse涓洪潪閲忓寲PUNC妯″瀷锛岄粯璁ゆ槸True
---port # 鏈嶅姟绔洃鍚殑绔彛鍙凤紝榛樿涓� 10095
---decoder-thread-num # 鏈嶅姟绔惎鍔ㄧ殑鎺ㄧ悊绾跨▼鏁帮紝榛樿涓� 8
---io-thread-num # 鏈嶅姟绔惎鍔ㄧ殑IO绾跨▼鏁帮紝榛樿涓� 1
---certfile <string> # ssl鐨勮瘉涔︽枃浠讹紝榛樿涓猴細../../../ssl_key/server.crt
---keyfile <string> # ssl鐨勫瘑閽ユ枃浠讹紝榛樿涓猴細../../../ssl_key/server.key
+--model-dir ASR妯″瀷璺緞锛岄粯璁や负锛�/workspace/models/asr
+--quantize True涓洪噺鍖朅SR妯″瀷锛孎alse涓洪潪閲忓寲ASR妯″瀷锛岄粯璁ゆ槸True
+--vad-dir VAD妯″瀷璺緞锛岄粯璁や负锛�/workspace/models/vad
+--vad-quant True涓洪噺鍖朧AD妯″瀷锛孎alse涓洪潪閲忓寲VAD妯″瀷锛岄粯璁ゆ槸True
+--punc-dir PUNC妯″瀷璺緞锛岄粯璁や负锛�/workspace/models/punc
+--punc-quant True涓洪噺鍖朠UNC妯″瀷锛孎alse涓洪潪閲忓寲PUNC妯″瀷锛岄粯璁ゆ槸True
+--port 鏈嶅姟绔洃鍚殑绔彛鍙凤紝榛樿涓� 10095
+--decoder-thread-num 鏈嶅姟绔惎鍔ㄧ殑鎺ㄧ悊绾跨▼鏁帮紝榛樿涓� 8
+--io-thread-num 鏈嶅姟绔惎鍔ㄧ殑IO绾跨▼鏁帮紝榛樿涓� 1
+--certfile ssl鐨勮瘉涔︽枃浠讹紝榛樿涓猴細../../../ssl_key/server.crt
+--keyfile ssl鐨勫瘑閽ユ枃浠讹紝榛樿涓猴細../../../ssl_key/server.key
```
-## <a id="anchor-1">妯″瀷璧勬簮鍑嗗</a>
+## 妯″瀷璧勬簮鍑嗗
濡傛灉鎮ㄩ�夋嫨閫氳繃funasr-wss-server浠嶮odelscope涓嬭浇妯″瀷锛屽彲浠ヨ烦杩囨湰姝ラ銆�
FunASR绂荤嚎鏂囦欢杞啓鏈嶅姟涓殑vad銆乤sr鍜宲unc妯″瀷璧勬簮鍧囨潵鑷狹odelscope锛屾ā鍨嬪湴鍧�璇﹁涓嬭〃锛�
-| 妯″瀷 | Modelscope閾炬帴 |
-|------|------------------------------------------------------------------------------------------------------------------|
-| VAD | https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary |
-| ASR | https://www.modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary |
-| PUNC | https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/summary |
+| 妯″瀷 | Modelscope閾炬帴 |
+|------|---------------------------------------------------------------------------------------------------------------|
+| VAD | https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx/summary |
+| ASR | https://www.modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx/summary |
+| PUNC | https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx/summary |
-绂荤嚎鏂囦欢杞啓鏈嶅姟涓儴缃茬殑鏄噺鍖栧悗鐨凮NNX妯″瀷锛屼笅闈粙缁嶄笅濡備綍瀵煎嚭ONNX妯″瀷鍙婂叾閲忓寲锛氭偍鍙互閫夋嫨浠嶮odelscope瀵煎嚭ONNX妯″瀷銆佷粠鏈湴鏂囦欢瀵煎嚭ONNX妯″瀷鎴栬�呬粠finetune鍚庣殑璧勬簮瀵煎嚭妯″瀷锛�
+绂荤嚎鏂囦欢杞啓鏈嶅姟涓儴缃茬殑鏄噺鍖栧悗鐨凮NNX妯″瀷锛屼笅闈粙缁嶄笅濡備綍瀵煎嚭ONNX妯″瀷鍙婂叾閲忓寲锛氭偍鍙互閫夋嫨浠嶮odelscope瀵煎嚭ONNX妯″瀷銆佷粠finetune鍚庣殑璧勬簮瀵煎嚭妯″瀷锛�
### 浠嶮odelscope瀵煎嚭ONNX妯″瀷
@@ -153,22 +217,6 @@
--type 妯″瀷绫诲瀷锛岀洰鍓嶆敮鎸� ONNX銆乼orch
--quantize int8妯″瀷閲忓寲
```
-
-### 浠庢湰鍦版枃浠跺鍑篛NNX妯″瀷
-
-璁剧疆model name涓烘ā鍨嬫湰鍦拌矾寰勶紝瀵煎嚭閲忓寲鍚庣殑ONNX妯″瀷锛�
-
-```shell
-python -m funasr.export.export_model --model-name /workspace/models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize True
-```
-鍛戒护鍙傛暟浠嬬粛锛�
-```text
---model-name 妯″瀷鏈湴璺緞锛屼緥濡�/workspace/models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
---export-dir ONNX妯″瀷瀵煎嚭鍦板潃
---type 妯″瀷绫诲瀷锛岀洰鍓嶆敮鎸� ONNX銆乼orch
---quantize int8妯″瀷閲忓寲
-```
-
### 浠巉inetune鍚庣殑璧勬簮瀵煎嚭妯″瀷
鍋囧鎮ㄦ兂閮ㄧ讲finetune鍚庣殑妯″瀷锛屽彲浠ュ弬鑰冨涓嬫楠わ細
@@ -179,36 +227,18 @@
python -m funasr.export.export_model --model-name /path/to/finetune/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize True
```
-## 瀹㈡埛绔惎鍔�
-鍦ㄦ湇鍔″櫒涓婂畬鎴怓unASR绂荤嚎鏂囦欢杞啓鏈嶅姟閮ㄧ讲浠ュ悗锛屽彲浠ラ�氳繃濡備笅鐨勬楠ゆ潵娴嬭瘯鍜屼娇鐢ㄧ绾挎枃浠惰浆鍐欐湇鍔°�傜洰鍓岶unASR-bin鏀寔澶氱鏂瑰紡鍚姩瀹㈡埛绔紝濡備笅鏄熀浜巔ython-client銆乧++-client鐨勫懡浠よ瀹炰緥鍙婅嚜瀹氫箟瀹㈡埛绔疻ebsocket閫氫俊鍗忚锛�
-### python-client
-```shell
-python wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "./data/wav.scp" --send_without_sleep --output_dir "./results"
-```
-鍛戒护鍙傛暟浠嬬粛锛�
-```text
---host # 鏈嶅姟绔痠p鍦板潃锛屾湰鏈烘祴璇曞彲璁剧疆涓� 127.0.0.1
---port # 鏈嶅姟绔洃鍚鍙ｅ彿
---audio_in # 闊抽杈撳叆锛岃緭鍏ュ彲浠ユ槸锛歸av璺緞 鎴栬�� wav.scp璺緞锛坘aldi鏍煎紡鐨剋av list锛寃av_id \t wav_path锛�
---output_dir # 璇嗗埆缁撴灉杈撳嚭璺緞
---ssl # 鏄惁浣跨敤SSL鍔犲瘑锛岄粯璁や娇鐢�
---mode # offline妯″紡
-```
+## 濡備綍瀹氬埗鏈嶅姟閮ㄧ讲
-### c++-client锛�
-```shell
-. /funasr-wss-client --server-ip 127.0.0.1 --port 10095 --wav-path test.wav --thread-num 1 --is-ssl 1
-```
-鍛戒护鍙傛暟浠嬬粛锛�
-```text
---server-ip # 鏈嶅姟绔痠p鍦板潃锛屾湰鏈烘祴璇曞彲璁剧疆涓� 127.0.0.1
---port # 鏈嶅姟绔洃鍚鍙ｅ彿
---wav-path # 闊抽杈撳叆锛岃緭鍏ュ彲浠ユ槸锛歸av璺緞 鎴栬�� wav.scp璺緞锛坘aldi鏍煎紡鐨剋av list锛寃av_id \t wav_path锛�
---thread-num # 瀹㈡埛绔嚎绋嬫暟
---is-ssl # 鏄惁浣跨敤SSL鍔犲瘑锛岄粯璁や娇鐢�
-```
+FunASR-runtime鐨勪唬鐮佸凡寮�婧愶紝濡傛灉鏈嶅姟绔拰瀹㈡埛绔笉鑳藉緢濂界殑婊¤冻鎮ㄧ殑闇�姹傦紝鎮ㄥ彲浠ユ牴鎹嚜宸辩殑闇�姹傝繘琛岃繘涓�姝ョ殑寮�鍙戯細
+### c++ 瀹㈡埛绔細
+
+https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/websocket
+
+### python 瀹㈡埛绔細
+
+https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/python/websocket
### 鑷畾涔夊鎴风锛�
@@ -223,16 +253,6 @@
{"is_speaking": False}
```
-## 濡備綍瀹氬埗鏈嶅姟閮ㄧ讲
-
-FunASR-runtime鐨勪唬鐮佸凡寮�婧愶紝濡傛灉鏈嶅姟绔拰瀹㈡埛绔笉鑳藉緢濂界殑婊¤冻鎮ㄧ殑闇�姹傦紝鎮ㄥ彲浠ユ牴鎹嚜宸辩殑闇�姹傝繘琛岃繘涓�姝ョ殑寮�鍙戯細
-### c++ 瀹㈡埛绔細
-
-https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/websocket
-
-### python 瀹㈡埛绔細
-
-https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/python/websocket
### c++ 鏈嶅姟绔細
#### VAD
@@ -265,4 +285,4 @@
FUNASR_RESULT result=CTTransformerInfer(punc_hanlde, txt_str.c_str(), RASR_NONE, NULL);
// 鍏朵腑锛歱unc_hanlde涓篊TTransformerInit杩斿洖鍊硷紝txt_str涓烘枃鏈�
```
-浣跨敤绀轰緥璇﹁锛歨ttps://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/onnxruntime/bin/funasr-onnx-offline-punc.cpp
+浣跨敤绀轰緥璇﹁锛歨ttps://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/onnxruntime/bin/funasr-onnx-offline-punc.cpp
\ No newline at end of file
diff --git a/funasr/runtime/docs/SDK_tutorial.md b/funasr/runtime/docs/SDK_tutorial.md
index 0943466..c8f9971 100644
--- a/funasr/runtime/docs/SDK_tutorial.md
+++ b/funasr/runtime/docs/SDK_tutorial.md
@@ -275,7 +275,7 @@
Looking in indexes: http://mirrors.cloud.aliyuncs.com/pypi/simple/
Requirement already satisfied: websockets in /usr/local/lib/python3.8/dist-packages (from -r /root/funasr_samples/python/requirements_client.txt (line 1)) (11.0.3)
- Run python3 /root/funasr_samples/python/wss_client_asr.py --host 127.0.0.1 --port 10095 --mode offline --audio_in /root/funasr_samples/audio/asr_example.wav --send_without_sleep --output_dir ./funasr_samples/python
+ Run python3 /root/funasr_samples/python/funasr_wss_client.py --host 127.0.0.1 --port 10095 --mode offline --audio_in /root/funasr_samples/audio/asr_example.wav --send_without_sleep --output_dir ./funasr_samples/python
...
...
@@ -284,7 +284,7 @@
Exception: sent 1000 (OK); then received 1000 (OK)
end
- If failed, you can try (python3 /root/funasr_samples/python/wss_client_asr.py --host 127.0.0.1 --port 10095 --mode offline --audio_in /root/funasr_samples/audio/asr_example.wav --send_without_sleep --output_dir ./funasr_samples/python) in your Shell.
+ If failed, you can try (python3 /root/funasr_samples/python/funasr_wss_client.py --host 127.0.0.1 --port 10095 --mode offline --audio_in /root/funasr_samples/audio/asr_example.wav --send_without_sleep --output_dir ./funasr_samples/python) in your Shell.
```
@@ -292,7 +292,7 @@
If you want to directly run the client for testing, you can refer to the following simple instructions, taking the Python version as an example:
```shell
-python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --send_without_sleep --output_dir "./results"
+python3 funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --send_without_sleep --output_dir "./results"
```
Command parameter instructions:
diff --git a/funasr/runtime/docs/SDK_tutorial_zh.md b/funasr/runtime/docs/SDK_tutorial_zh.md
index bb4c5ed..8c476a3 100644
--- a/funasr/runtime/docs/SDK_tutorial_zh.md
+++ b/funasr/runtime/docs/SDK_tutorial_zh.md
@@ -10,32 +10,36 @@
- 閰嶇疆2: 锛圶86锛岃绠楀瀷锛夛紝16鏍竩CPU锛屽唴瀛�32G锛屽崟鏈哄彲浠ユ敮鎸佸ぇ绾�64璺殑璇锋眰
- 閰嶇疆3: 锛圶86锛岃绠楀瀷锛夛紝64鏍竩CPU锛屽唴瀛�128G锛屽崟鏈哄彲浠ユ敮鎸佸ぇ绾�200璺殑璇锋眰
+璇︾粏鎬ц兘娴嬭瘯鎶ュ憡锛圼鐐瑰嚮姝ゅ](./benchmark_onnx_cpp.md)锛�
+
浜戞湇鍔″巶鍟嗭紝閽堝鏂扮敤鎴凤紝鏈�3涓湀鍏嶈垂璇曠敤娲诲姩锛岀敵璇锋暀绋嬶紙[鐐瑰嚮姝ゅ](./aliyun_server_tutorial.md)锛�
## 蹇�熶笂鎵�
### 鏈嶅姟绔惎鍔�
+`娉ㄦ剰`锛氫竴閿儴缃插伐鍏凤紝杩囩▼鍒嗕负锛氬畨瑁卍ocker銆佷笅杞絛ocker闀滃儚銆佸惎鍔ㄦ湇鍔°�傚鏋滅敤鎴峰笇鏈涚洿鎺ヤ粠FunASR docker闀滃儚鍚姩锛屽彲浠ュ弬鑰冨紑鍙戞寚鍗楋紙[鐐瑰嚮姝ゅ](./SDK_advanced_guide_offline_zh.md)锛�
+
涓嬭浇閮ㄧ讲宸ュ叿`funasr-runtime-deploy-offline-cpu-zh.sh`
```shell
curl -O https://raw.githubusercontent.com/alibaba-damo-academy/FunASR/main/funasr/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh;
-# 濡傞亣鍒扮綉缁滈棶棰橈紝涓浗澶ч檰鐢ㄦ埛锛屽彲浠ョ敤涓笅闈㈢殑鍛戒护锛�
+# 濡傞亣鍒扮綉缁滈棶棰橈紝涓浗澶ч檰鐢ㄦ埛锛屽彲浠ヤ娇鐢ㄤ笅闈㈢殑鍛戒护锛�
# curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/funasr-runtime-deploy-offline-cpu-zh.sh;
```
-鎵ц閮ㄧ讲宸ュ叿锛屽湪鎻愮ず澶勮緭鍏ュ洖杞﹂敭鍗冲彲瀹屾垚鏈嶅姟绔畨瑁呬笌閮ㄧ讲銆傜洰鍓嶄究鎹烽儴缃插伐鍏锋殏鏃朵粎鏀寔Linux鐜锛屽叾浠栫幆澧冮儴缃插弬鑰冨紑鍙戞寚鍗楋紙[鐐瑰嚮姝ゅ](./SDK_advanced_guide_zh.md)锛�
+鎵ц閮ㄧ讲宸ュ叿锛屽湪鎻愮ず澶勮緭鍏ュ洖杞﹂敭鍗冲彲瀹屾垚鏈嶅姟绔畨瑁呬笌閮ㄧ讲銆傜洰鍓嶄究鎹烽儴缃插伐鍏锋殏鏃朵粎鏀寔Linux鐜锛屽叾浠栫幆澧冮儴缃插弬鑰冨紑鍙戞寚鍗楋紙[鐐瑰嚮姝ゅ](./SDK_advanced_guide_offline_zh.md)锛�
```shell
sudo bash funasr-runtime-deploy-offline-cpu-zh.sh install --workspace /root/funasr-runtime-resources
```
### 瀹㈡埛绔祴璇曚笌浣跨敤
-杩愯涓婇潰瀹夎鎸囦护鍚庯紝浼氬湪/root/funasr-runtime-resources锛堥粯璁ゅ畨瑁呯洰褰曪級涓笅杞藉鎴风娴嬭瘯宸ュ叿鐩綍samples锛�
+杩愯涓婇潰瀹夎鎸囦护鍚庯紝浼氬湪/root/funasr-runtime-resources锛堥粯璁ゅ畨瑁呯洰褰曪級涓笅杞藉鎴风娴嬭瘯宸ュ叿鐩綍samples锛堟墜鍔ㄤ笅杞斤紝[鐐瑰嚮姝ゅ](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/sample/funasr_samples.tar.gz)锛夛紝
鎴戜滑浠ython璇█瀹㈡埛绔负渚嬶紝杩涜璇存槑锛屾敮鎸佸绉嶉煶棰戞牸寮忚緭鍏ワ紙.wav, .pcm, .mp3绛夛級锛屼篃鏀寔瑙嗛杈撳叆(.mp4绛�)锛屼互鍙婂鏂囦欢鍒楄〃wav.scp杈撳叆锛屽叾浠栫増鏈鎴风璇峰弬鑰冩枃妗ｏ紙[鐐瑰嚮姝ゅ](#瀹㈡埛绔敤娉曡瑙�)锛�
```shell
-python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --output_dir "./results"
+python3 funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav"
```
## 瀹㈡埛绔敤娉曡瑙�
@@ -54,7 +58,7 @@
鑻ユ兂鐩存帴杩愯client杩涜娴嬭瘯锛屽彲鍙傝�冨涓嬬畝鏄撹鏄庯紝浠ython鐗堟湰涓轰緥锛�
```shell
-python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --output_dir "./results"
+python3 funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav"
```
鍛戒护鍙傛暟璇存槑锛�
@@ -63,7 +67,8 @@
--port 10095 閮ㄧ讲绔彛鍙�
--mode offline琛ㄧず绂荤嚎鏂囦欢杞啓
--audio_in 闇�瑕佽繘琛岃浆鍐欑殑闊抽鏂囦欢锛屾敮鎸佹枃浠惰矾寰勶紝鏂囦欢鍒楄〃wav.scp
---output_dir 璇嗗埆缁撴灉淇濆瓨璺緞
+--thread_num 璁剧疆骞跺彂鍙戦�佺嚎绋嬫暟锛岄粯璁や负1
+--ssl 璁剧疆鏄惁寮�鍚痵sl璇佷功鏍￠獙锛岄粯璁�1寮�鍚紝璁剧疆涓�0鍏抽棴
```
### cpp-client
@@ -78,6 +83,8 @@
--server-ip 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛岄渶瑕佹敼涓洪儴缃叉満鍣╥p
--port 10095 閮ㄧ讲绔彛鍙�
--wav-path 闇�瑕佽繘琛岃浆鍐欑殑闊抽鏂囦欢锛屾敮鎸佹枃浠惰矾寰�
+--thread_num 璁剧疆骞跺彂鍙戦�佺嚎绋嬫暟锛岄粯璁や负1
+--ssl 璁剧疆鏄惁寮�鍚痵sl璇佷功鏍￠獙锛岄粯璁�1寮�鍚紝璁剧疆涓�0鍏抽棴
```
### Html缃戦〉鐗�
@@ -108,6 +115,13 @@
sudo bash funasr-runtime-deploy-offline-cpu-zh.sh stop
```
+### 閲婃斁FunASR鏈嶅姟
+
+閲婃斁宸茬粡閮ㄧ讲鐨凢unASR鏈嶅姟銆�
+```shell
+sudo bash funasr-runtime-deploy-offline-cpu-zh.sh remove
+```
+
### 閲嶅惎FunASR鏈嶅姟
鏍规嵁涓婃涓�閿儴缃茬殑璁剧疆閲嶅惎鍚姩FunASR鏈嶅姟銆�
@@ -134,6 +148,7 @@
sudo bash funasr-runtime-deploy-offline-cpu-zh.sh update [--host_port | --docker_port] <port number>
sudo bash funasr-runtime-deploy-offline-cpu-zh.sh update [--decode_thread_num | --io_thread_num] <the number of threads>
sudo bash funasr-runtime-deploy-offline-cpu-zh.sh update [--workspace] <workspace in local>
+sudo bash funasr-runtime-deploy-offline-cpu-zh.sh update [--ssl] <0: close SSL; 1: open SSL, default:1>
e.g
sudo bash funasr-runtime-deploy-offline-cpu-zh.sh update --decode_thread_num 32
@@ -143,7 +158,7 @@
## 鏈嶅姟绔惎鍔ㄨ繃绋嬮厤缃瑙�
-##### 閫夋嫨FunASR Docker闀滃儚
+### 閫夋嫨FunASR Docker闀滃儚
鎺ㄨ崘閫夋嫨1)浣跨敤鎴戜滑鐨勬渶鏂板彂甯冪増闀滃儚锛屼篃鍙�夋嫨鍘嗗彶鐗堟湰銆�
```text
[1/5]
@@ -157,7 +172,7 @@
```
-##### 璁剧疆瀹夸富鏈烘彁渚涚粰FunASR鐨勭鍙�
+### 璁剧疆瀹夸富鏈烘彁渚涚粰FunASR鐨勭鍙�
璁剧疆鎻愪緵缁橠ocker鐨勫涓绘満绔彛锛岄粯璁や负10095銆傝淇濊瘉姝ょ鍙ｅ彲鐢ㄣ��
```text
[2/5]
@@ -167,6 +182,22 @@
The port in Docker for FunASR server is 10095
```
+### 璁剧疆SSL
+
+榛樿寮�鍚疭SL鏍￠獙锛屽鏋滈渶瑕佸叧闂紝鍙互鍦ㄥ惎鍔ㄦ椂璁剧疆
+```shell
+sudo bash funasr-runtime-deploy-offline-cpu-zh.sh --ssl 0
+```
+
+## 鑱旂郴鎴戜滑
+
+鍦ㄦ偍浣跨敤杩囩▼涓紝濡傛灉閬囧埌闂锛屾杩庡姞鍏ョ敤鎴风兢杩涜鍙嶉
+
+
+| 閽夐拤鐢ㄦ埛缇� | 寰俊 |
+|:----------------------------------------------------------------------------:|:-----------------------------------------------------:|
+| <div align="left"><img src="../../../docs/images/dingding.jpg" width="250"/> | <img src="../../../docs/images/wechat.png" width="232"/></div> |
+
## 瑙嗛demo
diff --git a/funasr/runtime/html5/readme.md b/funasr/runtime/html5/readme.md
index 0c1eba0..c85641c 100644
--- a/funasr/runtime/html5/readme.md
+++ b/funasr/runtime/html5/readme.md
@@ -41,7 +41,7 @@
`Tips:` asr service and html5 service should be deployed on the same device.
```shell
cd ../python/websocket
-python wss_srv_asr.py --port 10095
+python funasr_wss_server.py --port 10095
```
diff --git a/funasr/runtime/html5/readme_cn.md b/funasr/runtime/html5/readme_cn.md
index b859387..dfc27c9 100644
--- a/funasr/runtime/html5/readme_cn.md
+++ b/funasr/runtime/html5/readme_cn.md
@@ -49,7 +49,7 @@
#### wss鏂瑰紡
```shell
cd ../python/websocket
-python wss_srv_asr.py --port 10095
+python funasr_wss_server.py --port 10095
```
### 娴忚鍣ㄦ墦寮�鍦板潃
diff --git a/funasr/runtime/python/onnxruntime/setup.py b/funasr/runtime/python/onnxruntime/setup.py
index a6f6828..6cc1989 100644
--- a/funasr/runtime/python/onnxruntime/setup.py
+++ b/funasr/runtime/python/onnxruntime/setup.py
@@ -13,7 +13,7 @@
MODULE_NAME = 'funasr_onnx'
-VERSION_NUM = '0.1.1'
+VERSION_NUM = '0.1.2'
setuptools.setup(
name=MODULE_NAME,
diff --git a/funasr/runtime/python/websocket/README.md b/funasr/runtime/python/websocket/README.md
index ed44795..686ad86 100644
--- a/funasr/runtime/python/websocket/README.md
+++ b/funasr/runtime/python/websocket/README.md
@@ -24,7 +24,7 @@
##### API-reference
```shell
-python wss_srv_asr.py \
+python funasr_wss_server.py \
--port [port id] \
--asr_model [asr model_name] \
--asr_model_online [asr model_name] \
@@ -36,7 +36,7 @@
```
##### Usage examples
```shell
-python wss_srv_asr.py --port 10095 --asr_model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" --asr_model_online "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online"
+python funasr_wss_server.py --port 10095
```
## For the client
@@ -47,11 +47,19 @@
cd funasr/runtime/python/websocket
pip install -r requirements_client.txt
```
+If you want infer from videos, you should install `ffmpeg`
+```shell
+apt-get install -y ffmpeg #ubuntu
+# yum install -y ffmpeg # centos
+# brew install ffmpeg # mac
+# winget install ffmpeg # wins
+pip3 install websockets ffmpeg-python
+```
### Start client
#### API-reference
```shell
-python wss_client_asr.py \
+python funasr_wss_client.py \
--host [ip_address] \
--port [port id] \
--chunk_size ["5,10,5"=600ms, "8,8,4"=480ms] \
@@ -59,9 +67,8 @@
--words_max_print [max number of words to print] \
--audio_in [if set, loadding from wav.scp, else recording from mircrophone] \
--output_dir [if set, write the results to output_dir] \
---send_without_sleep [only set for offline] \
---ssl [1 for wss connect, 0 for ws, default is 1] \
--mode [`online` for streaming asr, `offline` for non-streaming, `2pass` for unifying streaming and non-streaming asr] \
+--thread_num [thread_num for send data]
```
#### Usage examples
@@ -69,36 +76,36 @@
Recording from mircrophone
```shell
# --chunk_interval, "10": 600/10=60ms, "5"=600/5=120ms, "20": 600/12=30ms
-python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode offline --chunk_interval 10 --words_max_print 100
+python funasr_wss_client.py --host "0.0.0.0" --port 10095 --mode offline
```
Loadding from wav.scp(kaldi style)
```shell
# --chunk_interval, "10": 600/10=60ms, "5"=600/5=120ms, "20": 600/12=30ms
-python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode offline --chunk_interval 10 --words_max_print 100 --audio_in "./data/wav.scp" --output_dir "./results"
+python funasr_wss_client.py --host "0.0.0.0" --port 10095 --mode offline --audio_in "./data/wav.scp" --output_dir "./results"
```
##### ASR streaming client
Recording from mircrophone
```shell
# --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms
-python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode online --chunk_size "5,10,5" --words_max_print 100
+python funasr_wss_client.py --host "0.0.0.0" --port 10095 --mode online --chunk_size "5,10,5"
```
Loadding from wav.scp(kaldi style)
```shell
# --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms
-python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode online --chunk_size "5,10,5" --audio_in "./data/wav.scp" --output_dir "./results"
+python funasr_wss_client.py --host "0.0.0.0" --port 10095 --mode online --chunk_size "5,10,5" --audio_in "./data/wav.scp" --output_dir "./results"
```
##### ASR offline/online 2pass client
Recording from mircrophone
```shell
# --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms
-python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode 2pass --chunk_size "8,8,4"
+python funasr_wss_client.py --host "0.0.0.0" --port 10095 --mode 2pass --chunk_size "8,8,4"
```
Loadding from wav.scp(kaldi style)
```shell
# --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms
-python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode 2pass --chunk_size "8,8,4" --audio_in "./data/wav.scp" --output_dir "./results"
+python funasr_wss_client.py --host "0.0.0.0" --port 10095 --mode 2pass --chunk_size "8,8,4" --audio_in "./data/wav.scp" --output_dir "./results"
```
## Acknowledge
1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR).
diff --git a/funasr/runtime/python/websocket/wss_client_asr.py b/funasr/runtime/python/websocket/funasr_wss_client.py
similarity index 82%
rename from funasr/runtime/python/websocket/wss_client_asr.py
rename to funasr/runtime/python/websocket/funasr_wss_client.py
index 45b8ac4..72121f7 100644
--- a/funasr/runtime/python/websocket/wss_client_asr.py
+++ b/funasr/runtime/python/websocket/funasr_wss_client.py
@@ -8,11 +8,10 @@
import json
import traceback
from multiprocessing import Process
-from funasr.fileio.datadir_writer import DatadirWriter
+# from funasr.fileio.datadir_writer import DatadirWriter
import logging
-SUPPORT_AUDIO_TYPE_SETS = ['.wav', '.pcm']
logging.basicConfig(level=logging.ERROR)
parser = argparse.ArgumentParser()
@@ -42,10 +41,10 @@
action="store_true",
default=True,
help="if audio_in is set, send_without_sleep")
-parser.add_argument("--test_thread_num",
+parser.add_argument("--thread_num",
type=int,
default=1,
- help="test_thread_num")
+ help="thread_num")
parser.add_argument("--words_max_print",
type=int,
default=10000,
@@ -72,11 +71,13 @@
voices = Queue()
offline_msg_done=False
-
-ibest_writer = None
+
if args.output_dir is not None:
- writer = DatadirWriter(args.output_dir)
- ibest_writer = writer[f"1best_recog"]
+ # if os.path.exists(args.output_dir):
+ # os.remove(args.output_dir)
+
+ if not os.path.exists(args.output_dir):
+ os.makedirs(args.output_dir)
async def record_microphone():
@@ -100,11 +101,13 @@
message = json.dumps({"mode": args.mode, "chunk_size": args.chunk_size, "chunk_interval": args.chunk_interval,
"wav_name": "microphone", "is_speaking": True})
- voices.put(message)
+ #voices.put(message)
+ await websocket.send(message)
while True:
data = stream.read(CHUNK)
message = data
- voices.put(message)
+ #voices.put(message)
+ await websocket.send(message)
await asyncio.sleep(0.005)
async def record_from_scp(chunk_begin, chunk_size):
@@ -134,8 +137,17 @@
frames = wav_file.readframes(wav_file.getnframes())
audio_bytes = bytes(frames)
else:
- raise NotImplementedError(
- f'Not supported audio type')
+ import ffmpeg
+ try:
+ # This launches a subprocess to decode audio while down-mixing and resampling as necessary.
+ # Requires the ffmpeg CLI and `ffmpeg-python` package to be installed.
+ audio_bytes, _ = (
+ ffmpeg.input(wav_path, threads=0)
+ .output("-", format="s16le", acodec="pcm_s16le", ac=1, ar=16000)
+ .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
+ )
+ except ffmpeg.Error as e:
+ raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e
# stride = int(args.chunk_size/1000*16000*2)
stride = int(60 * args.chunk_size[1] / args.chunk_interval / 1000 * 16000 * 2)
@@ -164,10 +176,9 @@
sleep_duration = 0.001 if args.mode == "offline" else 60 * args.chunk_size[1] / args.chunk_interval / 1000
await asyncio.sleep(sleep_duration)
- # when all data sent, we need to close websocket
- while not voices.empty():
- await asyncio.sleep(1)
- await asyncio.sleep(3)
+
+ if not args.mode=="offline":
+ await asyncio.sleep(2)
# offline model need to wait for message recved
if args.mode=="offline":
@@ -176,17 +187,18 @@
await asyncio.sleep(1)
await websocket.close()
-
-
-
-
-
+
+
async def message(id):
global websocket,voices,offline_msg_done
text_print = ""
text_print_2pass_online = ""
text_print_2pass_offline = ""
+ if args.output_dir is not None:
+ ibest_writer = open(os.path.join(args.output_dir, "text.{}".format(id)), "a", encoding="utf-8")
+ else:
+ ibest_writer = None
try:
while True:
@@ -194,9 +206,11 @@
meg = json.loads(meg)
wav_name = meg.get("wav_name", "demo")
text = meg["text"]
- if ibest_writer is not None:
- ibest_writer["text"][wav_name] = text
+ if ibest_writer is not None:
+ text_write_line = "{}\t{}\n".format(wav_name, text)
+ ibest_writer.write(text_write_line)
+
if meg["mode"] == "online":
text_print += "{}".format(text)
text_print = text_print[-args.words_max_print:]
@@ -204,10 +218,10 @@
print("\rpid" + str(id) + ": " + text_print)
elif meg["mode"] == "offline":
text_print += "{}".format(text)
- text_print = text_print[-args.words_max_print:]
- os.system('clear')
- print("\rpid" + str(id) + ": " + text_print)
- offline_msg_done=True
+ # text_print = text_print[-args.words_max_print:]
+ # os.system('clear')
+ print("\rpid" + str(id) + ": " + wav_name + ": " + text_print)
+ offline_msg_done = True
else:
if meg["mode"] == "2pass-online":
text_print_2pass_online += "{}".format(text)
@@ -219,6 +233,7 @@
text_print = text_print[-args.words_max_print:]
os.system('clear')
print("\rpid" + str(id) + ": " + text_print)
+ offline_msg_done=True
except Exception as e:
print("Exception:", e)
@@ -227,17 +242,6 @@
-async def print_messge():
- global websocket
- while True:
- try:
- meg = await websocket.recv()
- meg = json.loads(meg)
- print(meg)
- except Exception as e:
- print("Exception:", e)
- #traceback.print_exc()
- exit(0)
async def ws_client(id, chunk_begin, chunk_size):
if args.audio_in is None:
@@ -262,7 +266,6 @@
task = asyncio.create_task(record_from_scp(i, 1))
else:
task = asyncio.create_task(record_microphone())
- #task2 = asyncio.create_task(ws_send())
task3 = asyncio.create_task(message(str(id)+"_"+str(i))) #processid+fileid
await asyncio.gather(task, task3)
exit(0)
@@ -291,21 +294,19 @@
wav_name = wav_splits[0] if len(wav_splits) > 1 else "demo"
wav_path = wav_splits[1] if len(wav_splits) > 1 else wav_splits[0]
audio_type = os.path.splitext(wav_path)[-1].lower()
- if audio_type not in SUPPORT_AUDIO_TYPE_SETS:
- raise NotImplementedError(
- f'Not supported audio type: {audio_type}')
+
total_len = len(wavs)
- if total_len >= args.test_thread_num:
- chunk_size = int(total_len / args.test_thread_num)
- remain_wavs = total_len - chunk_size * args.test_thread_num
+ if total_len >= args.thread_num:
+ chunk_size = int(total_len / args.thread_num)
+ remain_wavs = total_len - chunk_size * args.thread_num
else:
chunk_size = 1
remain_wavs = 0
process_list = []
chunk_begin = 0
- for i in range(args.test_thread_num):
+ for i in range(args.thread_num):
now_chunk_size = chunk_size
if remain_wavs > 0:
now_chunk_size = chunk_size + 1
diff --git a/funasr/runtime/python/websocket/wss_srv_asr.py b/funasr/runtime/python/websocket/funasr_wss_server.py
similarity index 80%
rename from funasr/runtime/python/websocket/wss_srv_asr.py
rename to funasr/runtime/python/websocket/funasr_wss_server.py
index 09f2305..4929090 100644
--- a/funasr/runtime/python/websocket/wss_srv_asr.py
+++ b/funasr/runtime/python/websocket/funasr_wss_server.py
@@ -5,17 +5,64 @@
import logging
import tracemalloc
import numpy as np
+import argparse
import ssl
-from parse_args import args
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.utils.logger import get_logger
-from funasr.runtime.python.onnxruntime.funasr_onnx.utils.frontend import load_bytes
tracemalloc.start()
logger = get_logger(log_level=logging.CRITICAL)
logger.setLevel(logging.CRITICAL)
+
+parser = argparse.ArgumentParser()
+parser.add_argument("--host",
+ type=str,
+ default="0.0.0.0",
+ required=False,
+ help="host ip, localhost, 0.0.0.0")
+parser.add_argument("--port",
+ type=int,
+ default=10095,
+ required=False,
+ help="grpc server port")
+parser.add_argument("--asr_model",
+ type=str,
+ default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
+ help="model from modelscope")
+parser.add_argument("--asr_model_online",
+ type=str,
+ default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online",
+ help="model from modelscope")
+parser.add_argument("--vad_model",
+ type=str,
+ default="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
+ help="model from modelscope")
+parser.add_argument("--punc_model",
+ type=str,
+ default="damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727",
+ help="model from modelscope")
+parser.add_argument("--ngpu",
+ type=int,
+ default=1,
+ help="0 for cpu, 1 for gpu")
+parser.add_argument("--ncpu",
+ type=int,
+ default=4,
+ help="cpu cores")
+parser.add_argument("--certfile",
+ type=str,
+ default="./ssl_key/server.crt",
+ required=False,
+ help="certfile for ssl")
+
+parser.add_argument("--keyfile",
+ type=str,
+ default="./ssl_key/server.key",
+ required=False,
+ help="keyfile for ssl")
+args = parser.parse_args()
websocket_users = set()
@@ -185,8 +232,6 @@
async def async_asr(websocket, audio_in):
if len(audio_in) > 0:
# print(len(audio_in))
- audio_in = load_bytes(audio_in)
-
rec_result = inference_pipeline_asr(audio_in=audio_in,
param_dict=websocket.param_dict_asr)
# print(rec_result)
@@ -195,13 +240,12 @@
param_dict=websocket.param_dict_punc)
# print("offline", rec_result)
if 'text' in rec_result:
- message = json.dumps({"mode": "2pass-offline", "text": rec_result["text"], "wav_name": websocket.wav_name})
+ message = json.dumps({"mode": websocket.mode, "text": rec_result["text"], "wav_name": websocket.wav_name})
await websocket.send(message)
async def async_asr_online(websocket, audio_in):
if len(audio_in) > 0:
- audio_in = load_bytes(audio_in)
# print(websocket.param_dict_asr_online.get("is_final", False))
rec_result = inference_pipeline_asr_online(audio_in=audio_in,
param_dict=websocket.param_dict_asr_online)
@@ -212,7 +256,7 @@
if "text" in rec_result:
if rec_result["text"] != "sil" and rec_result["text"] != "waiting_for_more_voice":
# print("online", rec_result)
- message = json.dumps({"mode": "2pass-online", "text": rec_result["text"], "wav_name": websocket.wav_name})
+ message = json.dumps({"mode": websocket.mode, "text": rec_result["text"], "wav_name": websocket.wav_name})
await websocket.send(message)
if len(args.certfile)>0:
diff --git a/funasr/runtime/python/websocket/parse_args.py b/funasr/runtime/python/websocket/parse_args.py
deleted file mode 100644
index ffecff7..0000000
--- a/funasr/runtime/python/websocket/parse_args.py
+++ /dev/null
@@ -1,50 +0,0 @@
-# -*- encoding: utf-8 -*-
-import argparse
-parser = argparse.ArgumentParser()
-parser.add_argument("--host",
- type=str,
- default="0.0.0.0",
- required=False,
- help="host ip, localhost, 0.0.0.0")
-parser.add_argument("--port",
- type=int,
- default=10095,
- required=False,
- help="grpc server port")
-parser.add_argument("--asr_model",
- type=str,
- default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
- help="model from modelscope")
-parser.add_argument("--asr_model_online",
- type=str,
- default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online",
- help="model from modelscope")
-parser.add_argument("--vad_model",
- type=str,
- default="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
- help="model from modelscope")
-parser.add_argument("--punc_model",
- type=str,
- default="damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727",
- help="model from modelscope")
-parser.add_argument("--ngpu",
- type=int,
- default=1,
- help="0 for cpu, 1 for gpu")
-parser.add_argument("--ncpu",
- type=int,
- default=4,
- help="cpu cores")
-parser.add_argument("--certfile",
- type=str,
- default="./ssl_key/server.crt",
- required=False,
- help="certfile for ssl")
-
-parser.add_argument("--keyfile",
- type=str,
- default="./ssl_key/server.key",
- required=False,
- help="keyfile for ssl")
-args = parser.parse_args()
-print(args)
\ No newline at end of file
diff --git a/funasr/runtime/python/websocket/requirements_client.txt b/funasr/runtime/python/websocket/requirements_client.txt
index 9498d6d..2cd4242 100644
--- a/funasr/runtime/python/websocket/requirements_client.txt
+++ b/funasr/runtime/python/websocket/requirements_client.txt
@@ -1,2 +1,2 @@
websockets
-pyaudio
\ No newline at end of file
+pyaudio
diff --git a/funasr/runtime/readme_cn.md b/funasr/runtime/readme_cn.md
index 492b97c..9ff90b2 100644
--- a/funasr/runtime/readme_cn.md
+++ b/funasr/runtime/readme_cn.md
@@ -14,7 +14,7 @@
## 涓枃绂荤嚎鏂囦欢杞啓鏈嶅姟閮ㄧ讲锛圕PU鐗堟湰锛�
-涓枃璇煶绂荤嚎鏂囦欢鏈嶅姟閮ㄧ讲锛圕PU鐗堟湰锛夛紝鎷ユ湁瀹屾暣鐨勮闊宠瘑鍒摼璺紝鍙互灏嗗嚑鍗佷釜灏忔椂鐨勯煶棰戜笌瑙嗛璇嗗埆鎴愬甫鏍囩偣鐨勬枃瀛楋紝鑰屼笖鏀寔涓婄櫨璺姹傚悓鏃惰繘琛岃浆鍐欍��
+涓枃璇煶绂荤嚎鏂囦欢鏈嶅姟閮ㄧ讲锛圕PU鐗堟湰锛夛紝鎷ユ湁瀹屾暣鐨勮闊宠瘑鍒摼璺紝鍙互灏嗗嚑鍗佷釜灏忔椂鐨勯暱闊抽涓庤棰戣瘑鍒垚甯︽爣鐐圭殑鏂囧瓧锛岃�屼笖鏀寔涓婄櫨璺姹傚悓鏃惰繘琛岃浆鍐欍��
涓轰簡鏀寔涓嶅悓鐢ㄦ埛鐨勯渶姹傦紝閽堝涓嶅悓鍦烘櫙锛屽噯澶囦簡涓嶅悓鐨勫浘鏂囨暀绋嬶細
### 渚挎嵎閮ㄧ讲鏁欑▼
@@ -28,4 +28,4 @@
### 鎶�鏈師鐞嗘彮绉�
-鏂囨。浠嬬粛浜嗚儗鍚庢妧鏈師鐞嗭紝璇嗗埆鍑嗙‘鐜囷紝璁＄畻鏁堢巼绛夛紝浠ュ強鏍稿績浼樺娍浠嬬粛锛氫究鎹枫�侀珮绮惧害銆侀珮鏁堢巼銆侀暱闊抽閾捐矾锛岃缁嗘枃妗ｅ弬鑰冿紙[鐐瑰嚮姝ゅ](https://mp.weixin.qq.com/s?__biz=MzA3MTQ0NTUyMw==&tempkey=MTIyNF84d05USjMxSEpPdk5GZXBJUFNJNzY0bU1DTkxhV19mcWY4MTNWQTJSYXhUaFgxOWFHZTZKR0JzWC1JRmRCdUxCX2NoQXg0TzFpNmVJX2R1WjdrcC02N2FEcUc3MDhzVVhpNWQ5clU4QUdqNFdkdjFYb18xRjlZMmc5c3RDOTl0U0NiRkJLb05ZZ0RmRlVkVjFCZnpXNWFBVlRhbXVtdWs4bUMwSHZnfn4%3D&chksm=1f2c3254285bbb42bc8f76a82e9c5211518a0bb1ff8c357d085c1b78f675ef2311f3be6e282c#rd)锛�
+鏂囨。浠嬬粛浜嗚儗鍚庢妧鏈師鐞嗭紝璇嗗埆鍑嗙‘鐜囷紝璁＄畻鏁堢巼绛夛紝浠ュ強鏍稿績浼樺娍浠嬬粛锛氫究鎹枫�侀珮绮惧害銆侀珮鏁堢巼銆侀暱闊抽閾捐矾锛岃缁嗘枃妗ｅ弬鑰冿紙[鐐瑰嚮姝ゅ](https://mp.weixin.qq.com/s/DHQwbgdBWcda0w_L60iUww)锛�
diff --git a/funasr/runtime/run_server.sh b/funasr/runtime/run_server.sh
old mode 100755
new mode 100644
diff --git a/funasr/runtime/websocket/CMakeLists.txt b/funasr/runtime/websocket/CMakeLists.txt
index 513e48d..51b0795 100644
--- a/funasr/runtime/websocket/CMakeLists.txt
+++ b/funasr/runtime/websocket/CMakeLists.txt
@@ -1,4 +1,4 @@
-cmake_minimum_required(VERSION 3.10)
+cmake_minimum_required(VERSION 3.16)
project(FunASRWebscoket)
diff --git a/funasr/runtime/websocket/funasr-wss-client.cpp b/funasr/runtime/websocket/funasr-wss-client.cpp
index eb94d14..b6d69f2 100644
--- a/funasr/runtime/websocket/funasr-wss-client.cpp
+++ b/funasr/runtime/websocket/funasr-wss-client.cpp
@@ -20,6 +20,7 @@
#include <websocketpp/config/asio_client.hpp>
#include <fstream>
#include <atomic>
+#include <thread>
#include <glog/logging.h>
#include "audio.h"
@@ -106,7 +107,7 @@
switch (msg->get_opcode()) {
case websocketpp::frame::opcode::text:
total_num=total_num+1;
- LOG(INFO)<<total_num<<",on_message = " << payload;
+ LOG(INFO)<< "Thread: " << this_thread::get_id() <<",on_message = " << payload;
if((total_num+1)==wav_index)
{
websocketpp::lib::error_code ec;
@@ -375,4 +376,4 @@
for (auto& t : client_threads) {
t.join();
}
-}
\ No newline at end of file
+}
diff --git a/funasr/utils/misc.py b/funasr/utils/misc.py
index f27a63c..e9050f5 100644
--- a/funasr/utils/misc.py
+++ b/funasr/utils/misc.py
@@ -12,7 +12,7 @@
return numel
-def int2vec(x, vec_dim=8, dtype=np.int):
+def int2vec(x, vec_dim=8, dtype=np.int32):
b = ('{:0' + str(vec_dim) + 'b}').format(x)
# little-endian order: lower bit first
return (np.array(list(b)[::-1]) == '1').astype(dtype)
diff --git a/funasr/version.txt b/funasr/version.txt
index 2228cad..1a5ac0d 100644
--- a/funasr/version.txt
+++ b/funasr/version.txt
@@ -1 +1 @@
-0.6.7
+0.6.9
diff --git a/tests/test_asr_inference_pipeline.py b/tests/test_asr_inference_pipeline.py
index 2b21acf..f68f29b 100644
--- a/tests/test_asr_inference_pipeline.py
+++ b/tests/test_asr_inference_pipeline.py
@@ -119,20 +119,28 @@
def test_paraformer_large_online_common(self):
inference_pipeline = pipeline(
task=Tasks.auto_speech_recognition,
- model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online')
+ model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
+ model_revision='v1.0.6',
+ update_model=False,
+ mode="paraformer_fake_streaming"
+ )
rec_result = inference_pipeline(
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
logger.info("asr inference result: {0}".format(rec_result))
- assert rec_result["text"] == "娆㈣繋澶� 瀹舵潵 浣撻獙杈� 鎽╅櫌鎺� 鍑虹殑 璇煶璇� 鍒ā 鍨�"
+ assert rec_result["text"] == "娆㈣繋澶у鏉ヤ綋楠岃揪鎽╅櫌鎺ㄥ嚭鐨勮闊宠瘑鍒ā鍨�"
def test_paraformer_online_common(self):
inference_pipeline = pipeline(
task=Tasks.auto_speech_recognition,
- model='damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online')
+ model='damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online',
+ model_revision='v1.0.6',
+ update_model=False,
+ mode="paraformer_fake_streaming"
+ )
rec_result = inference_pipeline(
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
logger.info("asr inference result: {0}".format(rec_result))
- assert rec_result["text"] == "娆㈣繋 澶у鏉� 浣撻獙杈� 鎽╅櫌鎺� 鍑虹殑 璇煶璇� 鍒ā 鍨�"
+ assert rec_result["text"] == "娆㈣繋澶у鏉ヤ綋楠岃揪鎽╅櫌鎺ㄥ嚭鐨勮闊宠瘑鍒ā鍨�"
def test_paraformer_tiny_commandword(self):
inference_pipeline = pipeline(
--
Gitblit v1.9.1