From afcbdd2d84cf59beb534b12829c67d61d83e605c Mon Sep 17 00:00:00 2001
From: ShiLiang Zhang <sly.zsl@alibaba-inc.com>
Date: 星期五, 21 七月 2023 11:40:11 +0800
Subject: [PATCH] Update README_zh.md
---
README_zh.md | 184 ++++++----------------------------------------
1 files changed, 24 insertions(+), 160 deletions(-)
diff --git a/README_zh.md b/README_zh.md
index ee9342d..b2c2c43 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -13,182 +13,44 @@
<div align="center">
<h4>
-<a href="#鏈�鏂板姩鎬�"> 鏈�鏂板姩鎬� </a>
+ <a href="#鏍稿績鍔熻兘"> 鏍稿績鍔熻兘 </a>
+锝�<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�
-
-
-### 璇煶璇嗗埆
-
-- 瀛︽湳妯″瀷锛�
- - Encoder-Decoder妯″瀷锛歔Transformer](egs/aishell/transformer)锛孾Conformer](egs/aishell/conformer)锛孾Branchformer](egs/aishell/branchformer)
- - Transducer妯″瀷锛歔RNNT锛堟祦寮忥級](egs/aishell/rnnt)锛孾BAT](egs/aishell/bat)
- - 闈炶嚜鍥炲綊妯″瀷锛歔Paraformer](egs/aishell/paraformer)
- - 澶氳璇濅汉璇嗗埆妯″瀷锛歔MFCCA](egs_modelscope/asr/mfcca)
-
-- 宸ヤ笟妯″瀷锛�
- - 涓枃閫氱敤妯″瀷锛歔Paraformer-large](egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch)锛孾Paraformer-large闀块煶棰戠増鏈琞(egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch)锛孾Paraformer-large娴佸紡鐗堟湰](egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online)
- - 涓枃閫氱敤鐑瘝妯″瀷锛歔Paraformer-large-contextual](egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404)锛�
- - 鑻辨枃閫氱敤妯″瀷锛歔Conformer]()
- - 娴佸紡绂荤嚎涓�浣撳寲妯″瀷锛� [16k UniASR闂藉崡璇璢(https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/summary)銆� [16k UniASR娉曡](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-fr-16k-common-vocab3472-tensorflow1-online/summary)銆� [16k UniASR寰疯](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-de-16k-common-vocab3690-tensorflow1-online/summary)銆� [16k UniASR瓒婂崡璇璢(https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-vi-16k-common-vocab1001-pytorch-online/summary)銆� [16k UniASR娉㈡柉璇璢(https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/summary),
- [16k UniASR缂呯敻璇璢(https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/summary)銆� [16k UniASR甯屼集鏉ヨ](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/summary)銆� [16k UniASR涔屽皵閮借](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/summary)銆� [8k UniASR涓枃閲戣瀺棰嗗煙](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-finance-vocab3445-online/summary)銆乕16k UniASR涓枃闊宠棰戦鍩焆(https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-16k-audio_and_video-vocab3445-online/summary)
-
-### 璇磋瘽浜鸿瘑鍒�
- - 璇磋瘽浜虹‘璁ゆā鍨嬶細[xvector](egs_modelscope/speaker_verification)
- - 璇磋瘽浜烘棩蹇楁ā鍨嬶細[SOND](egs/callhome/diarization/sond)
-
-### 鏍囩偣鎭㈠
- - 涓枃鏍囩偣妯″瀷锛歔CT-Transformer](egs_modelscope/punctuation/punc_ct-transformer_zh-cn-common-vocab272727-pytorch)锛孾CT-Transformer娴佸紡](egs_modelscope/punctuation/punc_ct-transformer_zh-cn-common-vadrealtime-vocab272727)
-
-### 绔偣妫�娴�
- - [FSMN-VAD](egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common)
-
-### 鏃堕棿鎴抽娴�
- - 瀛楃骇鍒ā鍨嬶細[TP-Aligner](egs_modelscope/tp/speech_timestamp_prediction-v1-16k-offline)
-
<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�
+- 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�佽闊崇鐐规娴嬶紙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瓑銆侳unASR鎻愪緵浜嗕究鎹风殑鑴氭湰鍜屾暀绋嬶紝鏀寔棰勮缁冨ソ鐨勬ā鍨嬬殑鎺ㄧ悊涓庡井璋冦��
+- 鎴戜滑鍦╗ModelScope](https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition)涓婂彂甯冧簡澶ч噺寮�婧愭暟鎹泦鎴栬�呮捣閲忓伐涓氭暟鎹缁冪殑妯″瀷锛屽彲浠ラ�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)浜嗚В妯″瀷鐨勮缁嗕俊鎭�備唬琛ㄦ�х殑[Paraformer](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)闈炶嚜鍥炲綊绔埌绔闊宠瘑鍒ā鍨嬪叿鏈夐珮绮惧害銆侀珮鏁堢巼銆佷究鎹烽儴缃茬殑浼樼偣锛屾敮鎸佸揩閫熸瀯寤鸿闊宠瘑鍒湇鍔★紝璇︾粏淇℃伅鍙互闃呰([鏈嶅姟閮ㄧ讲鏂囨。](funasr/runtime/readme_cn.md))銆�
+
+<a name="鏈�鏂板姩鎬�"></a>
+## 鏈�鏂板姩鎬�
+- 2023.07.17: BAT涓�绉嶄綆寤惰繜浣庡唴瀛樻秷鑰楃殑RNN-T妯″瀷鍙戝竷锛岃缁嗕俊鎭弬闃咃紙[BAT](egs/aishell/bat)锛�
+- 2023.07.03: 涓枃绂荤嚎鏂囦欢杞啓鏈嶅姟涓�閿儴缃茬殑CPU鐗堟湰鍙戝竷锛岃缁嗕俊鎭弬闃�([涓�閿儴缃叉枃妗([funasr/runtime/readme_cn.md](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/docs/SDK_tutorial_zh.md)))
+- 2023.06.26: ASRU2023 澶氶�氶亾澶氭柟浼氳杞綍鎸戞垬璧�2.0瀹屾垚绔炶禌缁撴灉鍏竷锛岃缁嗕俊鎭弬闃咃紙[M2MeT2.0](https://alibaba-damo-academy.github.io/FunASR/m2met2_cn/index.html)锛�
<a name="瀹夎鏁欑▼"></a>
## 瀹夎鏁欑▼
+FunASR瀹夎鏁欑▼璇烽槄璇伙紙[Installation](https://alibaba-damo-academy.github.io/FunASR/en/installation/installation.html)锛�
-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="鏈嶅姟閮ㄧ讲"></a>
+## 鏈嶅姟閮ㄧ讲
+FunASR鏀寔棰勮缁冩垨鑰呰繘涓�姝ュ井璋冪殑妯″瀷杩涜鏈嶅姟閮ㄧ讲銆傜洰鍓嶄腑鏂囩绾挎枃浠惰浆鍐欐湇鍔′竴閿儴缃茬殑CPU鐗堟湰宸茬粡鍙戝竷锛岃缁嗕俊鎭弬闃�([涓�閿儴缃叉枃妗([funasr/runtime/readme_cn.md](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/docs/SDK_tutorial_zh.md)))銆傛洿澶氭湇鍔￠儴缃茶缁嗕俊鎭彲浠ュ弬闃�([鏈嶅姟閮ㄧ讲鏂囨。](funasr/runtime/readme_cn.md))銆�
<a name="蹇�熷紑濮�"></a>
## 蹇�熷紑濮�
+FunASR鏀寔鏁颁竾灏忔椂宸ヤ笟鏁版嵁璁粌鐨勬ā鍨嬬殑鎺ㄧ悊鍜屽井璋冿紝璇︾粏淇℃伅鍙互鍙傞槄锛圼modelscope_egs](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/quick_start.html)锛夛紱涔熸敮鎸佸鏈爣鍑嗘暟鎹泦妯″瀷鐨勮缁冨拰寰皟锛岃缁嗕俊鎭彲浠ュ弬闃咃紙[egs](https://alibaba-damo-academy.github.io/FunASR/en/academic_recipe/asr_recipe.html)锛夈�� 妯″瀷鍖呭惈璇煶璇嗗埆锛圓SR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瓑锛岃缁嗘ā鍨嬪垪琛ㄥ彲浠ュ弬闃匸妯″瀷浠撳簱](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md)锛�
-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>
+<a name="绀惧尯浜ゆ祦"></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)
-
+濡傛灉鎮ㄥ湪浣跨敤涓亣鍒伴棶棰橈紝鍙互鐩存帴鍦╣ithub椤甸潰鎻怚ssues銆傛杩庤闊冲叴瓒ｇ埍濂借�呮壂鎻忎互涓嬬殑閽夐拤缇ゆ垨鑰呭井淇＄兢浜岀淮鐮佸姞鍏ョぞ鍖虹兢锛岃繘琛屼氦娴佸拰璁ㄨ銆�
| 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> |
@@ -202,12 +64,8 @@
## 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�
+椤圭洰閬靛惊[The MIT License](https://opensource.org/licenses/MIT)寮�婧愬崗璁紝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
@@ -218,6 +76,12 @@
year={2023},
booktitle={INTERSPEECH},
}
+@inproceedings{An2023bat,
+ author={Keyu An and Xian Shi and Shiliang Zhang},
+ title={BAT: Boundary aware transducer for memory-efficient and low-latency ASR},
+ 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}},
--
Gitblit v1.9.1