From 31bf3a88a09f6e7c895224f4dc75e8f2c138d5c8 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期一, 01 七月 2024 20:43:06 +0800
Subject: [PATCH] update funasr-runtime-sdk-gpu-0.1.1
---
runtime/docs/SDK_advanced_guide_offline_gpu_zh.md | 20 +++++++++++---------
runtime/readme_cn.md | 1 +
runtime/docs/SDK_advanced_guide_offline_gpu.md | 20 +++++++++++---------
README_zh.md | 1 +
runtime/readme.md | 1 +
README.md | 1 +
6 files changed, 26 insertions(+), 18 deletions(-)
diff --git a/README.md b/README.md
index a8b15e5..0cdbf64 100644
--- a/README.md
+++ b/README.md
@@ -29,6 +29,7 @@
<a name="whats-new"></a>
## What's new:
+- 2024/07/01: Offline File Transcription Service GPU 1.1 released, optimize BladeDISC model compatibility issues; ref to ([docs](runtime/readme.md))
- 2024/06/27: Offline File Transcription Service GPU 1.0 released, supporting dynamic batch processing and multi-threading concurrency. In the long audio test set, the single-thread RTF is 0.0076, and multi-threads' speedup is 1200+ (compared to 330+ on CPU); ref to ([docs](runtime/readme.md))
- 2024/05/15锛歟motion recognition models are new supported. [emotion2vec+large](https://modelscope.cn/models/iic/emotion2vec_plus_large/summary)锛孾emotion2vec+base](https://modelscope.cn/models/iic/emotion2vec_plus_base/summary)锛孾emotion2vec+seed](https://modelscope.cn/models/iic/emotion2vec_plus_seed/summary). currently supports the following categories: 0: angry 1: happy 2: neutral 3: sad 4: unknown.
- 2024/05/15: Offline File Transcription Service 4.5, Offline File Transcription Service of English 1.6锛孯eal-time Transcription Service 1.10 released锛宎dapting to FunASR 1.0 model structure锛�([docs](runtime/readme.md))
diff --git a/README_zh.md b/README_zh.md
index 169face..fe05f13 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -33,6 +33,7 @@
<a name="鏈�鏂板姩鎬�"></a>
## 鏈�鏂板姩鎬�
+- 2024/07/01锛氫腑鏂囩绾挎枃浠惰浆鍐欐湇鍔PU鐗堟湰 1.1鍙戝竷锛屼紭鍖朾ladedisc妯″瀷鍏煎鎬ч棶棰橈紱璇︾粏淇℃伅鍙傞槄([閮ㄧ讲鏂囨。](runtime/readme_cn.md))
- 2024/06/27锛氫腑鏂囩绾挎枃浠惰浆鍐欐湇鍔PU鐗堟湰 1.0鍙戝竷锛屾敮鎸佸姩鎬乥atch锛屾敮鎸佸璺苟鍙戯紝鍦ㄩ暱闊抽娴嬭瘯闆嗕笂鍗曠嚎RTF涓�0.0076锛屽绾垮姞閫熸瘮涓�1200+锛圕PU涓�330+锛夛紱璇︾粏淇℃伅鍙傞槄([閮ㄧ讲鏂囨。](runtime/readme_cn.md))
- 2024/05/15锛氭柊澧炲姞鎯呮劅璇嗗埆妯″瀷锛孾emotion2vec+large](https://modelscope.cn/models/iic/emotion2vec_plus_large/summary)锛孾emotion2vec+base](https://modelscope.cn/models/iic/emotion2vec_plus_base/summary)锛孾emotion2vec+seed](https://modelscope.cn/models/iic/emotion2vec_plus_seed/summary)锛岃緭鍑烘儏鎰熺被鍒负锛氱敓姘�/angry锛屽紑蹇�/happy锛屼腑绔�/neutral锛岄毦杩�/sad銆�
- 2024/05/15: 涓枃绂荤嚎鏂囦欢杞啓鏈嶅姟 4.5銆佽嫳鏂囩绾挎枃浠惰浆鍐欐湇鍔� 1.6銆佷腑鏂囧疄鏃惰闊冲惉鍐欐湇鍔� 1.10 鍙戝竷锛岄�傞厤FunASR 1.0妯″瀷缁撴瀯锛涜缁嗕俊鎭弬闃�([閮ㄧ讲鏂囨。](runtime/readme_cn.md))
diff --git a/runtime/docs/SDK_advanced_guide_offline_gpu.md b/runtime/docs/SDK_advanced_guide_offline_gpu.md
index 4b9e264..a94567b 100644
--- a/runtime/docs/SDK_advanced_guide_offline_gpu.md
+++ b/runtime/docs/SDK_advanced_guide_offline_gpu.md
@@ -12,6 +12,7 @@
| TIME | INFO | IMAGE VERSION | IMAGE ID |
|------------|----------------------------------------------------------------------------------------------------------------------------------|------------------------------|--------------|
+| 2024.07.01 | Optimize BladeDISC model compatibility issues | funasr-runtime-sdk-gpu-0.1.1 | b39c6fb16451 |
| 2024.06.27 | Offline File Transcription Software Package(GPU) 1.0 released | funasr-runtime-sdk-gpu-0.1.0 | b86066f4d018 |
@@ -27,9 +28,9 @@
### Pulling and launching images
Use the following command to pull and launch the Docker image for the FunASR runtime-SDK:
```shell
-sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-gpu-0.1.0
+sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-gpu-0.1.1
-sudo docker run --gpus=all -p 10098:10095 -it --privileged=true -v /root:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-gpu-0.1.0
+sudo docker run --gpus=all -p 10098:10095 -it --privileged=true -v /root:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-gpu-0.1.1
```
Introduction to command parameters:
@@ -45,16 +46,17 @@
nohup bash 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-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-torchscript \
+ --model-dir damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch \
--punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx \
--lm-dir damo/speech_ngram_lm_zh-cn-ai-wesp-fst \
--itn-dir thuduj12/fst_itn_zh \
--hotword /workspace/models/hotwords.txt > log.txt 2>&1 &
+***When the service starts for the first time, it will export the TorchScript model, which may take some time. Please be patient***
# If you want to close ssl锛宲lease add锛�--certfile 0
# If you want to deploy the timestamp or nn hotword model, please set --model-dir to the corresponding model:
-# damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-torchscript锛坱imestamp锛�
-# damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404-torchscript锛坔otword锛�
+# damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch锛坱imestamp锛�
+# damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404锛坔otword锛�
# If you want to load hotwords on the server side, please configure the hotwords in the host machine file ./funasr-runtime-resources/models/hotwords.txt (docker mapping address: /workspace/models/hotwords.txt):
# One hotword per line, format (hotword weight): 闃块噷宸村反 20"
```
@@ -67,7 +69,7 @@
cd /workspace/FunASR/runtime
nohup bash run_server.sh \
--download-model-dir /workspace/models \
- --model-dir damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-torchscript \
+ --model-dir damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch \
--vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
--punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx \
--itn-dir thuduj12/fst_itn_zh \
@@ -104,8 +106,8 @@
### Modifying Models and Other Parameters
To replace the currently used model or other parameters, you need to first shut down the FunASR service, make the necessary modifications to the parameters you want to replace, and then restart the FunASR service. The model should be either an ASR/VAD/PUNC model from ModelScope or a fine-tuned model obtained from ModelScope.
```text
-# For example, to replace the ASR model with damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-torchscript, use the following parameter setting --model-dir
- --model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-torchscript
+# For example, to replace the ASR model with damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch, use the following parameter setting --model-dir
+ --model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
# Set the port number using --port
--port <port number>
# Set the number of inference threads the server will start using --decoder-thread-num
@@ -118,7 +120,7 @@
After executing the above command, the real-time speech transcription service will be started. If the model is specified as a ModelScope model id, the following models will be automatically downloaded from ModelScope:
[FSMN-VAD](https://www.modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx/summary),
-[Paraformer-lagre](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-torchscript/summary),
+[Paraformer-lagre](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary),
[CT-Transformer](https://www.modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx/summary),
[FST-ITN](https://www.modelscope.cn/models/thuduj12/fst_itn_zh/summary),
[Ngram lm](https://www.modelscope.cn/models/damo/speech_ngram_lm_zh-cn-ai-wesp-fst/summary)
diff --git a/runtime/docs/SDK_advanced_guide_offline_gpu_zh.md b/runtime/docs/SDK_advanced_guide_offline_gpu_zh.md
index d709559..e9aa814 100644
--- a/runtime/docs/SDK_advanced_guide_offline_gpu_zh.md
+++ b/runtime/docs/SDK_advanced_guide_offline_gpu_zh.md
@@ -10,6 +10,7 @@
| 鏃堕棿 | 璇︽儏 | 闀滃儚鐗堟湰 | 闀滃儚ID |
|------------|---------------------------------------------------|------------------------------|--------------|
+| 2024.07.01 | 浼樺寲bladedisc妯″瀷鍏煎鎬ч棶棰� | funasr-runtime-sdk-gpu-0.1.1 | b39c6fb16451 |
| 2024.06.27 | 绂荤嚎鏂囦欢杞啓鏈嶅姟GPU鐗堟湰1.0 鍙戝竷 | funasr-runtime-sdk-gpu-0.1.0 | b86066f4d018 |
## 鏈嶅姟鍣ㄩ厤缃�
@@ -39,11 +40,11 @@
```shell
sudo docker pull \
- registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-gpu-0.1.0
+ registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-gpu-0.1.1
mkdir -p ./funasr-runtime-resources/models
sudo docker run --gpus=all -p 10098:10095 -it --privileged=true \
-v $PWD/funasr-runtime-resources/models:/workspace/models \
- registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-gpu-0.1.0
+ registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-gpu-0.1.1
```
### 鏈嶅姟绔惎鍔�
@@ -54,16 +55,17 @@
nohup bash 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-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-torchscript \
+ --model-dir damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch \
--punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx \
--lm-dir damo/speech_ngram_lm_zh-cn-ai-wesp-fst \
--itn-dir thuduj12/fst_itn_zh \
--hotword /workspace/models/hotwords.txt > log.txt 2>&1 &
+***鏈嶅姟棣栨鍚姩鏃朵細瀵煎嚭torchscript妯″瀷锛岃�楁椂杈冮暱锛岃鑰愬績绛夊緟***
# 濡傛灉鎮ㄦ兂鍏抽棴ssl锛屽鍔犲弬鏁帮細--certfile 0
# 榛樿鍔犺浇鏃堕棿鎴虫ā鍨嬶紝濡傛灉鎮ㄦ兂浣跨敤nn鐑瘝妯″瀷杩涜閮ㄧ讲锛岃璁剧疆--model-dir涓哄搴旀ā鍨嬶細
-# damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-torchscript锛堟椂闂存埑锛�
-# damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404-torchscript锛坣n鐑瘝锛�
+# damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch锛堟椂闂存埑锛�
+# damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404锛坣n鐑瘝锛�
# 濡傛灉鎮ㄦ兂鍦ㄦ湇鍔＄鍔犺浇鐑瘝锛岃鍦ㄥ涓绘満鏂囦欢./funasr-runtime-resources/models/hotwords.txt閰嶇疆鐑瘝锛坉ocker鏄犲皠鍦板潃涓�/workspace/models/hotwords.txt锛�:
# 姣忚涓�涓儹璇嶏紝鏍煎紡(鐑瘝 鏉冮噸)锛氶樋閲屽反宸� 20锛堟敞锛氱儹璇嶇悊璁轰笂鏃犻檺鍒讹紝浣嗕负浜嗗吋椤炬�ц兘鍜屾晥鏋滐紝寤鸿鐑瘝闀垮害涓嶈秴杩�10锛屼釜鏁颁笉瓒呰繃1k锛屾潈閲�1~100锛�
```
@@ -148,7 +150,7 @@
cd /workspace/FunASR/runtime
nohup bash run_server.sh \
--download-model-dir /workspace/models \
- --model-dir damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-torchscript \
+ --model-dir damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch \
--vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
--punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx \
--lm-dir damo/speech_ngram_lm_zh-cn-ai-wesp-fst \
@@ -187,8 +189,8 @@
### 淇敼妯″瀷鍙婂叾浠栧弬鏁�
鏇挎崲姝ｅ湪浣跨敤鐨勬ā鍨嬫垨鑰呭叾浠栧弬鏁帮紝闇�鍏堝叧闂璅unASR鏈嶅姟锛屼慨鏀归渶瑕佹浛鎹㈢殑鍙傛暟锛屽苟閲嶆柊鍚姩FunASR鏈嶅姟銆傚叾涓ā鍨嬮渶涓篗odelScope涓殑ASR/VAD/PUNC妯″瀷锛屾垨鑰呬粠ModelScope涓ā鍨媐inetune鍚庣殑妯″瀷銆�
```text
-# 渚嬪鏇挎崲ASR妯″瀷涓� damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-torchscript锛屽垯濡備笅璁剧疆鍙傛暟 --model-dir
- --model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-torchscript
+# 渚嬪鏇挎崲ASR妯″瀷涓� damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch锛屽垯濡備笅璁剧疆鍙傛暟 --model-dir
+ --model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
# 璁剧疆绔彛鍙� --port
--port <port number>
# 璁剧疆鏈嶅姟绔惎鍔ㄧ殑鎺ㄧ悊绾跨▼鏁� --decoder-thread-num
@@ -201,7 +203,7 @@
鎵ц涓婅堪鎸囦护鍚庯紝鍚姩绂荤嚎鏂囦欢杞啓鏈嶅姟銆傚鏋滄ā鍨嬫寚瀹氫负ModelScope涓璵odel id锛屼細鑷姩浠嶮oldeScope涓笅杞藉涓嬫ā鍨嬶細
[FSMN-VAD妯″瀷](https://www.modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx/summary),
-[Paraformer-lagre妯″瀷](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-torchscript/summary),
+[Paraformer-lagre妯″瀷](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary),
[CT-Transformer鏍囩偣棰勬祴妯″瀷](https://www.modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx/summary),
[鍩轰簬FST鐨勪腑鏂嘔TN](https://www.modelscope.cn/models/thuduj12/fst_itn_zh/summary),
[Ngram涓枃璇█妯″瀷](https://www.modelscope.cn/models/damo/speech_ngram_lm_zh-cn-ai-wesp-fst/summary)
diff --git a/runtime/readme.md b/runtime/readme.md
index eda90c3..539cc85 100644
--- a/runtime/readme.md
+++ b/runtime/readme.md
@@ -17,6 +17,7 @@
To meet the needs of different users, we have prepared different tutorials with text and images for both novice and advanced developers.
### Whats-new
+- 2024/07/01: File Transcription Service 1.1 GPU released, optimize BladeDISC model compatibility issues, docker image version funasr-runtime-sdk-gpu-0.1.1 (b39c6fb16451)
- 2024/06/27: File Transcription Service 1.0 GPU released, supporting dynamic batch processing and multi-threading concurrency. In the long audio test set, the single-thread RTF is 0.0076, and multi-threads' speedup is 1200+ (compared to 330+ on CPU), ref to([docs](./docs/benchmark_libtorch_cpp.md)) , docker image version funasr-runtime-sdk-gpu-0.1.0 (b86066f4d018)
### Advanced Development Guide
diff --git a/runtime/readme_cn.md b/runtime/readme_cn.md
index 997d465..29ea9b6 100644
--- a/runtime/readme_cn.md
+++ b/runtime/readme_cn.md
@@ -19,6 +19,7 @@
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
### 鏈�鏂板姩鎬�
+- 2024/07/01: 涓枃绂荤嚎鏂囦欢杞啓鏈嶅姟GPU 1.1 鍙戝竷锛屼紭鍖朾ladedisc妯″瀷鍏煎鎬ч棶棰橈紝dokcer闀滃儚鐗堟湰funasr-runtime-sdk-gpu-0.1.1 (b39c6fb16451)
- 2024/06/27: 涓枃绂荤嚎鏂囦欢杞啓鏈嶅姟GPU 1.0 鍙戝竷锛屾敮鎸佸姩鎬乥atch锛屾敮鎸佸璺苟鍙戯紝鍦ㄩ暱闊抽娴嬭瘯闆嗕笂鍗曠嚎RTF涓�0.0076锛屽绾垮姞閫熸瘮涓�1200+锛圕PU涓�330+锛夛紝璇﹁([鏂囨。](./docs/benchmark_libtorch_cpp.md))锛宒okcer闀滃儚鐗堟湰funasr-runtime-sdk-gpu-0.1.0 (b86066f4d018)
### 閮ㄧ讲涓庡紑鍙戞枃妗�
--
Gitblit v1.9.1