From 41c64e4729ca359f7212534055239c8289b5e2f4 Mon Sep 17 00:00:00 2001 From: hnluo <haoneng.lhn@alibaba-inc.com> Date: 星期四, 21 九月 2023 16:15:15 +0800 Subject: [PATCH] Merge pull request #975 from alibaba-damo-academy/main --- funasr/runtime/docs/SDK_advanced_guide_offline.md | 25 +++++++++++++++---------- 1 files changed, 15 insertions(+), 10 deletions(-) diff --git a/funasr/runtime/docs/SDK_advanced_guide_offline.md b/funasr/runtime/docs/SDK_advanced_guide_offline.md index e9a6a7d..63276eb 100644 --- a/funasr/runtime/docs/SDK_advanced_guide_offline.md +++ b/funasr/runtime/docs/SDK_advanced_guide_offline.md @@ -36,9 +36,9 @@ 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-0.2.1 +sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.2.2 -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-0.2.1 +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-0.2.2 ``` Introduction to command parameters: @@ -58,7 +58,8 @@ --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 > log.out 2>&1 & + --punc-dir damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx \ + --itn-dir thuduj12/fst_itn_zh > log.out 2>&1 & # If you want to close ssl锛宲lease add锛�--certfile 0 # If you want to deploy the timestamp or hotword model, please set --model-dir to the corresponding model: @@ -77,6 +78,7 @@ --model-dir damo/speech_paraformer-large_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_zh-cn-common-vocab272727-onnx \ + --itn-dir thuduj12/fst_itn_zh \ --decoder-thread-num 32 \ --io-thread-num 8 \ --port 10095 \ @@ -94,6 +96,7 @@ --vad-quant: True for quantized VAD model, False for non-quantized VAD model. Default is True. --punc-dir: Modelscope model ID. --punc-quant: True for quantized PUNC model, False for non-quantized PUNC model. Default is True. +--itn-dir modelscope model ID --port: Port number that the server listens on. Default is 10095. --decoder-thread-num: Number of inference threads that the server starts. Default is 8. --io-thread-num: Number of IO threads that the server starts. Default is 1. @@ -109,6 +112,7 @@ --model-dir /workspace/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \ --vad-dir /workspace/models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx \ --punc-dir /workspace/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx \ + --itn-dir /workspace/models/thuduj12/fst_itn_zh \ --decoder-thread-num 32 \ --io-thread-num 8 \ --port 10095 \ @@ -120,6 +124,7 @@ [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-onnx/summary) [CT-Transformer](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx/summary) +[FST-ITN](https://www.modelscope.cn/models/thuduj12/fst_itn_zh/summary) If you wish to deploy your fine-tuned model (e.g., 10epoch.pb), you need to manually rename the model to model.pb and replace the original model.pb in ModelScope. Then, specify the path as `model_dir`. @@ -143,7 +148,8 @@ --output_dir: the path to the recognition result output. --ssl: whether to use SSL encryption. The default is to use SSL. --mode: offline mode. ---hotword If am is hotword model, setting hotword: *.txt(one hotword perline) or hotwords seperate by space (could be: 闃块噷宸村反 杈炬懇闄�) +--hotword: If am is hotword model, setting hotword: *.txt(one hotword perline) or hotwords seperate by space (could be: 闃块噷宸村反 杈炬懇闄�) +--use_itn: whether to use itn, the default value is 1 for enabling and 0 for disabling. ``` ### c++-client @@ -154,13 +160,12 @@ Introduction to command parameters: ```text ---host: the IP address of the server. It can be set to 127.0.0.1 for local testing. +--server-ip: the IP address of the server. It can be set to 127.0.0.1 for local testing. --port: the port number of the server listener. ---audio_in: the audio input. Input can be a path to a wav file or a wav.scp file (a Kaldi-formatted wav list in which each line includes a wav_id followed by a tab and a wav_path). ---output_dir: the path to the recognition result output. ---ssl: whether to use SSL encryption. The default is to use SSL. ---mode: offline mode. ---hotword If am is hotword model, setting hotword: *.txt(one hotword perline) or hotwords seperate by space (could be: 闃块噷宸村反 杈炬懇闄�) +--wav-path: the audio input. Input can be a path to a wav file or a wav.scp file (a Kaldi-formatted wav list in which each line includes a wav_id followed by a tab and a wav_path). +--is-ssl: whether to use SSL encryption. The default is to use SSL. +--hotword: If am is hotword model, setting hotword: *.txt(one hotword perline) or hotwords seperate by space (could be: 闃块噷宸村反 杈炬懇闄�) +--use-itn: whether to use itn, the default value is 1 for enabling and 0 for disabling. ``` ### Custom client -- Gitblit v1.9.1