提交

kongdeqiang

5 天以前 28ccfbfc51068a663a80764e14074df5edf2b5ba

 runtime/docs/SDK_advanced_guide_offline.md

@@ -12,7 +12,10 @@

| TIME       | INFO                                                                                                                             | IMAGE VERSION                | IMAGE ID     |
|------------|----------------------------------------------------------------------------------------------------------------------------------|------------------------------|--------------|
| 2024.01.25 | Optimized the VAD (Voice Activity Detection) data processing method, significantly reducing peak memory usage; memory leak optimization| funasr-runtime-sdk-cpu-0.4.2 | 35817a3c4f17 |
| 2024.09.26 | Fix memory leak, Support the SensevoiceSmall onnx model                 | funasr-runtime-sdk-cpu-0.4.6  | 8651c6b8a1ae |
| 2024.05.15 | Adapting to FunASR 1.0 model structure | funasr-runtime-sdk-cpu-0.4.5 | 058b9882ae67 |
| 2024.03.05 | docker image supports ARM64 platform, update modelscope | funasr-runtime-sdk-cpu-0.4.4 | 2dc87b86dc49 |
| 2024.01.25 | Optimized the VAD (Voice Activity Detection) data processing method, significantly reducing peak memory usage; memory leak optimization| funasr-runtime-sdk-cpu-0.4.2 | befdc7b179ed |
| 2024.01.08 | optimized format sentence-level timestamps | funasr-runtime-sdk-cpu-0.4.1 | 0250f8ef981b |
| 2024.01.03 | Added support for 8k models, optimized timestamp mismatch issues and added sentence-level timestamps, improved the effectiveness of English word FST hotwords, supported automated configuration of thread parameters, and fixed known crash issues as well as memory leak problems. | funasr-runtime-sdk-cpu-0.4.0 | c4483ee08f04 |
| 2023.11.08 | supporting punc-large model, Ngram model, fst hotwords, server-side loading of hotwords, adaptation to runtime structure changes | funasr-runtime-sdk-cpu-0.3.0 | caa64bddbb43 |
@@ -33,9 +36,9 @@
### 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-cpu-0.4.1
sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.4.7

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-0.4.1
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-0.4.7
```

Introduction to command parameters: 
@@ -55,7 +58,7 @@
  --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.out 2>&1 &
  --hotword /workspace/models/hotwords.txt > log.txt 2>&1 &

# If you want to close ssl，please add：--certfile 0
# If you want to deploy the timestamp or nn hotword model, please set --model-dir to the corresponding model:
@@ -73,14 +76,14 @@
cd /workspace/FunASR/runtime
nohup bash run_server.sh \
  --download-model-dir /workspace/models \
  --model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
  --model-dir damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx \
  --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 \
  --lm-dir damo/speech_ngram_lm_zh-cn-ai-wesp-fst \
  --certfile  ../../../ssl_key/server.crt \
  --keyfile ../../../ssl_key/server.key \
  --hotword ../../hotwords.txt > log.out 2>&1 &
  --hotword ../../hotwords.txt > log.txt 2>&1 &
 ```

Introduction to run_server.sh parameters: