From 71f3d70dd765ad3ffd6ca80c99219e8c6d72f89e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=9B=BE=E8=81=AA?= Date: Tue, 7 Nov 2023 19:35:37 +0800 Subject: [PATCH] update docs --- runtime/docs/SDK_advanced_guide_offline.md | 6 +++--- runtime/docs/SDK_advanced_guide_offline_en.md | 6 +++--- runtime/docs/SDK_advanced_guide_offline_en_zh.md | 6 +++--- runtime/docs/SDK_advanced_guide_offline_zh.md | 6 +++--- runtime/docs/docker_offline_cpu_en_lists | 2 +- runtime/docs/docker_offline_cpu_zh_lists | 2 +- runtime/run_server.sh | 4 ++-- runtime/websocket/bin/funasr-wss-server.cpp | 2 +- 8 files changed, 17 insertions(+), 17 deletions(-) diff --git a/runtime/docs/SDK_advanced_guide_offline.md b/runtime/docs/SDK_advanced_guide_offline.md index 091036543..dd1372683 100644 --- a/runtime/docs/SDK_advanced_guide_offline.md +++ b/runtime/docs/SDK_advanced_guide_offline.md @@ -57,7 +57,7 @@ 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_asr_nat-zh-cn-16k-common-vocab8404-onnx \ - --punc-dir damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx \ + --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 > log.out 2>&1 & @@ -78,7 +78,7 @@ nohup bash run_server.sh \ --download-model-dir /workspace/models \ --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 \ + --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 \ --decoder-thread-num 32 \ @@ -133,7 +133,7 @@ To replace the currently used model or other parameters, you need to first shut 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-onnx/summary), -[CT-Transformer](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx/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_en.md b/runtime/docs/SDK_advanced_guide_offline_en.md index e4650382e..317f8a958 100644 --- a/runtime/docs/SDK_advanced_guide_offline_en.md +++ b/runtime/docs/SDK_advanced_guide_offline_en.md @@ -58,7 +58,7 @@ 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_asr_nat-en-16k-common-vocab10020-onnx \ - --punc-dir damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx > log.out 2>&1 & + --punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx > log.out 2>&1 & # If you want to close ssl，please add：--certfile 0 @@ -74,7 +74,7 @@ nohup bash run_server.sh \ --download-model-dir /workspace/models \ --model-dir damo/speech_paraformer-large_asr_nat-en-16k-common-vocab10020-onnx \ --vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \ - --punc-dir damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx \ + --punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx \ --decoder-thread-num 32 \ --io-thread-num 8 \ --port 10095 \ @@ -125,7 +125,7 @@ To replace the currently used model or other parameters, you need to first shut 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-en-16k-common-vocab10020-onnx/summary), -[CT-Transformer](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx/summary) +[CT-Transformer](https://www.modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx/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`. diff --git a/runtime/docs/SDK_advanced_guide_offline_en_zh.md b/runtime/docs/SDK_advanced_guide_offline_en_zh.md index 3bd2b7723..bbdb8a930 100644 --- a/runtime/docs/SDK_advanced_guide_offline_en_zh.md +++ b/runtime/docs/SDK_advanced_guide_offline_en_zh.md @@ -49,7 +49,7 @@ 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_asr_nat-en-16k-common-vocab10020-onnx \ - --punc-dir damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx > log.out 2>&1 & + --punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx > log.out 2>&1 & # 如果您想关闭ssl，增加参数：--certfile 0 @@ -166,7 +166,7 @@ nohup bash run_server.sh \ --download-model-dir /workspace/models \ --model-dir damo/speech_paraformer-large_asr_nat-en-16k-common-vocab10020-onnx \ --vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \ - --punc-dir damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx \ + --punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx \ --decoder-thread-num 32 \ --io-thread-num 8 \ --port 10095 \ @@ -216,7 +216,7 @@ kill -9 PID 执行上述指令后，启动英文离线文件转写服务。如果模型指定为ModelScope中model id，会自动从MoldeScope中下载如下模型： [FSMN-VAD模型](https://www.modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx/summary), [Paraformer-lagre模型](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-en-16k-common-vocab10020-onnx/summary), -[CT-Transformer标点预测模型](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx/summary) +[CT-Transformer标点预测模型](https://www.modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx/summary) 如果，您希望部署您finetune后的模型（例如10epoch.pb），需要手动将模型重命名为model.pb，并将原modelscope中模型model.pb替换掉，将路径指定为`model_dir`即可。 diff --git a/runtime/docs/SDK_advanced_guide_offline_zh.md b/runtime/docs/SDK_advanced_guide_offline_zh.md index 8655efc1c..71d1012b2 100644 --- a/runtime/docs/SDK_advanced_guide_offline_zh.md +++ b/runtime/docs/SDK_advanced_guide_offline_zh.md @@ -49,7 +49,7 @@ 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_asr_nat-zh-cn-16k-common-vocab8404-onnx \ - --punc-dir damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx \ + --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 > log.out 2>&1 & @@ -169,7 +169,7 @@ nohup bash run_server.sh \ --download-model-dir /workspace/models \ --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 \ + --punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx \ --itn-dir thuduj12/fst_itn_zh \ --decoder-thread-num 32 \ --io-thread-num 8 \ @@ -222,7 +222,7 @@ kill -9 PID 执行上述指令后，启动离线文件转写服务。如果模型指定为ModelScope中model id，会自动从MoldeScope中下载如下模型： [FSMN-VAD模型](https://www.modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx/summary), [Paraformer-lagre模型](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx/summary), -[CT-Transformer标点预测模型](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx/summary), +[CT-Transformer标点预测模型](https://www.modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx/summary), [基于FST的中文ITN](https://www.modelscope.cn/models/thuduj12/fst_itn_zh/summary), [Ngram中文语言模型](https://www.modelscope.cn/models/damo/speech_ngram_lm_zh-cn-ai-wesp-fst/summary) diff --git a/runtime/docs/docker_offline_cpu_en_lists b/runtime/docs/docker_offline_cpu_en_lists index fb3192f2a..3a20a3435 100644 --- a/runtime/docs/docker_offline_cpu_en_lists +++ b/runtime/docs/docker_offline_cpu_en_lists @@ -5,4 +5,4 @@ DEFAULT_ASR_MODEL: DEFAULT_VAD_MODEL: damo/speech_fsmn_vad_zh-cn-16k-common-onnx DEFAULT_PUNC_MODEL: - damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx + damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx diff --git a/runtime/docs/docker_offline_cpu_zh_lists b/runtime/docs/docker_offline_cpu_zh_lists index 4651784f9..5d1cd200c 100644 --- a/runtime/docs/docker_offline_cpu_zh_lists +++ b/runtime/docs/docker_offline_cpu_zh_lists @@ -9,7 +9,7 @@ DEFAULT_ASR_MODEL: DEFAULT_VAD_MODEL: damo/speech_fsmn_vad_zh-cn-16k-common-onnx DEFAULT_PUNC_MODEL: - damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx + damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx DEFAULT_LM_MODEL: damo/speech_ngram_lm_zh-cn-ai-wesp-fst NONE diff --git a/runtime/run_server.sh b/runtime/run_server.sh index 8f6ccbf4b..ab1cff76c 100644 --- a/runtime/run_server.sh +++ b/runtime/run_server.sh @@ -2,9 +2,9 @@ download_model_dir="/workspace/models" 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" +punc_dir="damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx" itn_dir="thuduj12/fst_itn_zh" -lm_dir="" +lm_dir="damo/speech_ngram_lm_zh-cn-ai-wesp-fst" decoder_thread_num=32 io_thread_num=8 port=10095 diff --git a/runtime/websocket/bin/funasr-wss-server.cpp b/runtime/websocket/bin/funasr-wss-server.cpp index c285fd3b1..66a9a58ff 100644 --- a/runtime/websocket/bin/funasr-wss-server.cpp +++ b/runtime/websocket/bin/funasr-wss-server.cpp @@ -108,7 +108,7 @@ int main(int argc, char* argv[]) { TCLAP::ValueArg am_scale("", AM_SCALE, "the acoustic scale for beam searching ", false, 10.0, "float"); TCLAP::ValueArg lm_dir("", LM_DIR, - "the LM model path, which contains compiled models: TLG.fst, config.yaml ", false, "", "string"); + "the LM model path, which contains compiled models: TLG.fst, config.yaml ", false, "damo/speech_ngram_lm_zh-cn-ai-wesp-fst", "string"); TCLAP::ValueArg lm_revision( "", "lm-revision", "LM model revision", false, "v1.0.1", "string"); TCLAP::ValueArg hotword("", HOTWORD,