From 28ccfbfc51068a663a80764e14074df5edf2b5ba Mon Sep 17 00:00:00 2001 From: kongdeqiang <kongdeqiang960204@163.com> Date: 星期五, 13 三月 2026 17:41:41 +0800 Subject: [PATCH] 提交 --- runtime/docs/SDK_advanced_guide_online.md | 30 +++++++++++++++++------------- 1 files changed, 17 insertions(+), 13 deletions(-) diff --git a/runtime/docs/SDK_advanced_guide_online.md b/runtime/docs/SDK_advanced_guide_online.md index fbc7d27..8dc0f48 100644 --- a/runtime/docs/SDK_advanced_guide_online.md +++ b/runtime/docs/SDK_advanced_guide_online.md @@ -8,6 +8,12 @@ | TIME | INFO | IMAGE VERSION | IMAGE ID | |------------|-------------------------------------------------------------------------------------|-------------------------------------|--------------| +| 2024.10.29 | The 2pass-offline mode supports the SensevoiceSmal model | funasr-runtime-sdk-online-cpu-0.1.12 | f5febc5cf13a | +| 2024.09.26 | Fix memory leak | funasr-runtime-sdk-online-cpu-0.1.11 | e51a36c42771 | +| 2024.05.15 | Adapting to FunASR 1.0 model structure | funasr-runtime-sdk-online-cpu-0.1.10 | 1c2adfcff84d | +| 2024.03.05 | docker image supports ARM64 platform, update modelscope | funasr-runtime-sdk-online-cpu-0.1.9 | 4a875e08c7a2 | +| 2024.01.25 | Optimization of the client-side | funasr-runtime-sdk-online-cpu-0.1.7 | 2aa23805572e | +| 2024.01.03 | The 2pass-offline mode supports Ngram language model decoding and WFST hotwords, while also addressing known crash issues and memory leak problems | funasr-runtime-sdk-online-cpu-0.1.6 | f99925110d27 | | 2023.11.09 | fix bug: without online results | funasr-runtime-sdk-online-cpu-0.1.5 | b16584b6d38b | | 2023.11.08 | supporting server-side loading of hotwords, adaptation to runtime structure changes | funasr-runtime-sdk-online-cpu-0.1.4 | 691974017c38 | | 2023.09.19 | supporting hotwords, timestamps, and ITN model in 2pass mode | funasr-runtime-sdk-online-cpu-0.1.2 | 7222c5319bcf | @@ -26,9 +32,9 @@ ### Pull Docker Image Use the following command to pull and start the FunASR software package docker image: ```shell -sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.2.0 +sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.13 mkdir -p ./funasr-runtime-resources/models -sudo docker run -p 10096:10095 -it --privileged=true -v $PWD/funasr-runtime-resources/models:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.2.0 +sudo docker run -p 10096:10095 -it --privileged=true -v $PWD/funasr-runtime-resources/models:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.13 ``` ### Launching the Server @@ -43,7 +49,7 @@ --online-model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online-onnx \ --punc-dir damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727-onnx \ --lm-dir damo/speech_ngram_lm_zh-cn-ai-wesp-fst \ - --itn-dir thuduj12/fst_itn_zh > log.out 2>&1 & + --itn-dir thuduj12/fst_itn_zh > log.txt 2>&1 & # If you want to close ssl锛宲lease add锛�--certfile 0 ``` @@ -57,7 +63,7 @@ For illustration, we will use the Python language client, which supports audio formats (.wav, .pcm) and a multi-file list wav.scp input. ```shell -python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode 2pass +python3 funasr_wss_client.py --host "127.0.0.1" --port 10096 --mode 2pass ``` ------------------ @@ -81,7 +87,7 @@ ```shell cd /workspace/FunASR/runtime nohup bash run_server_2pass.sh \ - --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 \ --online-model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online-onnx \ --vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \ --punc-dir damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727-onnx \ @@ -89,13 +95,14 @@ --itn-dir thuduj12/fst_itn_zh \ --certfile ../../../ssl_key/server.crt \ --keyfile ../../../ssl_key/server.key \ - --hotword ../../hotwords.txt > log.out 2>&1 & + --hotword ../../hotwords.txt > log.txt 2>&1 & # 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: -# speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx锛坱imestamp锛� -# damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404-onnx锛坔otword锛� - +# If you want to deploy the SenseVoiceSmall, timestamp or nn hotword model, please set --model-dir to the corresponding model: +# iic/SenseVoiceSmall-onnx +# speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx锛坱imestamp锛� +# damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404-onnx锛坔otword锛� +# The ASR results 鈥�<|zh|><|NEUTRAL|><|Speech|> 鈥� in SenseVoiceSmall-onnx means spoken language銆乻peech emotion銆乤udio event ``` ### More details about the script run_server_2pass.sh: @@ -103,11 +110,8 @@ --download-model-dir: Model download address, download models from Modelscope by setting the model ID. --model-dir: modelscope model ID or local model path. --online-model-dir modelscope model ID ---quantize: True for quantized ASR model, False for non-quantized ASR model. Default is True. --vad-dir: modelscope model ID or local model path. ---vad-quant: True for quantized VAD model, False for non-quantized VAD model. Default is True. --punc-dir: modelscope model ID or local model path. ---punc-quant: True for quantized PUNC model, False for non-quantized PUNC model. Default is True. --lm-dir modelscope model ID or local model path. --itn-dir modelscope model ID or local model path. --port: Port number that the server listens on. Default is 10095. -- Gitblit v1.9.1