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/websocket/bin/funasr-wss-server.cpp |  161 ++++++++++++++++++++++++++++++++++-------------------
 1 files changed, 104 insertions(+), 57 deletions(-)

diff --git a/runtime/websocket/bin/funasr-wss-server.cpp b/runtime/websocket/bin/funasr-wss-server.cpp
index 66a9a58..956c40e 100644
--- a/runtime/websocket/bin/funasr-wss-server.cpp
+++ b/runtime/websocket/bin/funasr-wss-server.cpp
@@ -4,14 +4,12 @@
  */
 /* 2022-2023 by zhaomingwork */
 
-// io server
-// Usage:funasr-wss-server  [--model_thread_num <int>] [--decoder_thread_num <int>]
-//                    [--io_thread_num <int>] [--port <int>] [--listen_ip
-//                    <string>] [--punc-quant <string>] [--punc-dir <string>]
-//                    [--vad-quant <string>] [--vad-dir <string>] [--quantize
-//                    <string>] --model-dir <string> [--] [--version] [-h]
 #include "websocket-server.h"
+#ifdef _WIN32
+#include "win_func.h"
+#else
 #include <unistd.h>
+#endif
 #include <fstream>
 #include "util.h"
 
@@ -28,28 +26,39 @@
 }
 
 int main(int argc, char* argv[]) {
+#ifdef _WIN32
+    #include <windows.h>
+    SetConsoleOutputCP(65001);
+#endif
   try {
 
     google::InitGoogleLogging(argv[0]);
     FLAGS_logtostderr = true;
-
-    TCLAP::CmdLine cmd("funasr-wss-server", ' ', "1.0");
+    std::string offline_version = "";
+#ifdef _WIN32
+    offline_version = "0.1.0";
+#endif
+    TCLAP::CmdLine cmd("funasr-wss-server", ' ', offline_version);
     TCLAP::ValueArg<std::string> download_model_dir(
         "", "download-model-dir",
         "Download model from Modelscope to download_model_dir",
         false, "/workspace/models", "string");
     TCLAP::ValueArg<std::string> model_dir(
         "", MODEL_DIR,
-        "default: /workspace/models/asr, the asr model path, which contains model_quant.onnx, config.yaml, am.mvn",
+        "default: /workspace/models/asr, the asr model path, which contains *.onnx/*.torchscript, config.yaml, am.mvn",
         false, "/workspace/models/asr", "string");
     TCLAP::ValueArg<std::string> model_revision(
         "", "model-revision",
         "ASR model revision",
-        false, "v1.2.1", "string");
+        false, "v2.0.5", "string");
     TCLAP::ValueArg<std::string> quantize(
         "", QUANTIZE,
         "true (Default), load the model of model_quant.onnx in model_dir. If set "
         "false, load the model of model.onnx in model_dir",
+        false, "true", "string");
+    TCLAP::ValueArg<std::string> bladedisc(
+        "", BLADEDISC, 
+        "true (Default), load the model of bladedisc in model_dir.", 
         false, "true", "string");
     TCLAP::ValueArg<std::string> vad_dir(
         "", VAD_DIR,
@@ -58,7 +67,7 @@
     TCLAP::ValueArg<std::string> vad_revision(
         "", "vad-revision",
         "VAD model revision",
-        false, "v1.2.0", "string");
+        false, "v2.0.6", "string");
     TCLAP::ValueArg<std::string> vad_quant(
         "", VAD_QUANT,
         "true (Default), load the model of model_quant.onnx in vad_dir. If set "
@@ -72,7 +81,7 @@
     TCLAP::ValueArg<std::string> punc_revision(
         "", "punc-revision",
         "PUNC model revision",
-        false, "v1.1.7", "string");
+        false, "v2.0.5", "string");
     TCLAP::ValueArg<std::string> punc_quant(
         "", PUNC_QUANT,
         "true (Default), load the model of model_quant.onnx in punc_dir. If set "
@@ -90,7 +99,7 @@
                                            "0.0.0.0", "string");
     TCLAP::ValueArg<int> port("", "port", "port", false, 10095, "int");
     TCLAP::ValueArg<int> io_thread_num("", "io-thread-num", "io thread num",
-                                       false, 8, "int");
+                                       false, 2, "int");
     TCLAP::ValueArg<int> decoder_thread_num(
         "", "decoder-thread-num", "decoder thread num", false, 8, "int");
     TCLAP::ValueArg<int> model_thread_num("", "model-thread-num",
@@ -110,12 +119,14 @@
     TCLAP::ValueArg<std::string> lm_dir("", LM_DIR,
         "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<std::string> lm_revision(
-        "", "lm-revision", "LM model revision", false, "v1.0.1", "string");
+        "", "lm-revision", "LM model revision", false, "v1.0.2", "string");
     TCLAP::ValueArg<std::string> hotword("", HOTWORD,
         "the hotword file, one hotword perline, Format: Hotword Weight (could be: 闃块噷宸村反 20)", 
         false, "/workspace/resources/hotwords.txt", "string");
     TCLAP::ValueArg<std::int32_t> fst_inc_wts("", FST_INC_WTS, 
         "the fst hotwords incremental bias", false, 20, "int32_t");
+    TCLAP::SwitchArg use_gpu("", INFER_GPU, "Whether to use GPU, default is false", false);
+    TCLAP::ValueArg<std::int32_t> batch_size("", BATCHSIZE, "batch_size for ASR model when using GPU", false, 4, "int32_t");
 
     // add file
     cmd.add(hotword);
@@ -130,6 +141,7 @@
     cmd.add(model_dir);
     cmd.add(model_revision);
     cmd.add(quantize);
+    cmd.add(bladedisc);
     cmd.add(vad_dir);
     cmd.add(vad_revision);
     cmd.add(vad_quant);
@@ -146,11 +158,14 @@
     cmd.add(io_thread_num);
     cmd.add(decoder_thread_num);
     cmd.add(model_thread_num);
+    cmd.add(use_gpu);
+    cmd.add(batch_size);
     cmd.parse(argc, argv);
 
     std::map<std::string, std::string> model_path;
     GetValue(model_dir, MODEL_DIR, model_path);
     GetValue(quantize, QUANTIZE, model_path);
+    GetValue(bladedisc, BLADEDISC, model_path);
     GetValue(vad_dir, VAD_DIR, model_path);
     GetValue(vad_quant, VAD_QUANT, model_path);
     GetValue(punc_dir, PUNC_DIR, model_path);
@@ -168,6 +183,8 @@
     global_beam_ = global_beam.getValue();
     lattice_beam_ = lattice_beam.getValue();
     am_scale_ = am_scale.getValue();
+    bool use_gpu_ = use_gpu.getValue();
+    int batch_size_ = batch_size.getValue();
 
     // Download model form Modelscope
     try{
@@ -181,8 +198,9 @@
         std::string s_punc_quant = model_path[PUNC_QUANT];
         std::string s_itn_path = model_path[ITN_DIR];
         std::string s_lm_path = model_path[LM_DIR];
+        std::string s_blade = model_path[BLADEDISC];
 
-        std::string python_cmd = "python -m funasr.utils.runtime_sdk_download_tool --type onnx --quantize True ";
+        std::string python_cmd = "python -m funasr.download.runtime_sdk_download_tool ";
 
         if(vad_dir.isSet() && !s_vad_path.empty()){
             std::string python_cmd_vad;
@@ -191,12 +209,12 @@
 
             if (access(s_vad_path.c_str(), F_OK) == 0){
                 // local
-                python_cmd_vad = python_cmd + " --model-name " + s_vad_path + " --export-dir ./ " + " --model_revision " + model_path["vad-revision"];
+                python_cmd_vad = python_cmd + " --type onnx " + " --quantize " + s_vad_quant + " --model-name " + s_vad_path + " --export-dir ./ " + " --model_revision " + model_path["vad-revision"];
                 down_vad_path  = s_vad_path;
             }else{
                 // modelscope
                 LOG(INFO) << "Download model: " <<  s_vad_path << " from modelscope: ";
-                python_cmd_vad = python_cmd + " --model-name " + s_vad_path + " --export-dir " + s_download_model_dir + " --model_revision " + model_path["vad-revision"];
+                python_cmd_vad = python_cmd + " --type onnx " + " --quantize " + s_vad_quant + " --model-name " + s_vad_path + " --export-dir " + s_download_model_dir + " --model_revision " + model_path["vad-revision"];
                 down_vad_path  = s_download_model_dir+"/"+s_vad_path;
             }
                 
@@ -224,42 +242,70 @@
             std::string python_cmd_asr;
             std::string down_asr_path;
             std::string down_asr_model;
+            std::string model_type = "onnx";
+
+            // modify model-revision by model name
+            size_t found = s_asr_path.find("speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404");
+            if (found != std::string::npos) {
+                model_path["model-revision"]="v2.0.5";
+            }
+
+            found = s_asr_path.find("speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404");
+            if (found != std::string::npos) {
+                model_path["model-revision"]="v2.0.5";
+            }
+
+            found = s_asr_path.find("speech_paraformer-large_asr_nat-en-16k-common-vocab10020");
+            if (found != std::string::npos) {
+                model_path["model-revision"]="v2.0.5";
+                s_itn_path="";
+                s_lm_path="";
+            }
+
+            found = s_asr_path.find(MODEL_SVS);
+            if (found != std::string::npos) {
+                model_path["model-revision"]="v2.0.5";
+                s_itn_path="";
+                model_path[ITN_DIR]="";
+                s_lm_path="";
+                model_path[LM_DIR]="";
+                s_punc_path="";
+                model_path[PUNC_DIR]="";
+            }
+
+            if (use_gpu_){
+                model_type = "torchscript";
+                if (s_blade=="true" || s_blade=="True" || s_blade=="TRUE"){
+                    model_type = "bladedisc";
+                }
+            }
 
             if (access(s_asr_path.c_str(), F_OK) == 0){
                 // local
-                python_cmd_asr = python_cmd + " --model-name " + s_asr_path + " --export-dir ./ " + " --model_revision " + model_path["model-revision"];
+                python_cmd_asr = python_cmd + " --type " + model_type + " --quantize " + s_asr_quant + " --model-name " + s_asr_path + " --export-dir ./ " + " --model_revision " + model_path["model-revision"];
                 down_asr_path  = s_asr_path;
             }else{
-                size_t found = s_asr_path.find("speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404");
-                if (found != std::string::npos) {
-                    model_path["model-revision"]="v1.2.4";
-                }
-
-                found = s_asr_path.find("speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404");
-                if (found != std::string::npos) {
-                    model_path["model-revision"]="v1.0.5";
-                }
-
-                found = s_asr_path.find("speech_paraformer-large_asr_nat-en-16k-common-vocab10020");
-                if (found != std::string::npos) {
-                    model_path["model-revision"]="v1.0.0";
-                    s_itn_path="";
-                    s_lm_path="";
-                }
-
                 // modelscope
                 LOG(INFO) << "Download model: " <<  s_asr_path << " from modelscope: ";
-                python_cmd_asr = python_cmd + " --model-name " + s_asr_path + " --export-dir " + s_download_model_dir + " --model_revision " + model_path["model-revision"];
+                python_cmd_asr = python_cmd + " --type " + model_type + " --quantize " + s_asr_quant + " --model-name " + s_asr_path + " --export-dir " + s_download_model_dir + " --model_revision " + model_path["model-revision"];
                 down_asr_path  = s_download_model_dir+"/"+s_asr_path;
             }
-                
-            int ret = system(python_cmd_asr.c_str());
-            if(ret !=0){
-                LOG(INFO) << "Failed to download model from modelscope. If you set local asr model path, you can ignore the errors.";
-            }
+            
             down_asr_model = down_asr_path+"/model_quant.onnx";
             if(s_asr_quant=="false" || s_asr_quant=="False" || s_asr_quant=="FALSE"){
                 down_asr_model = down_asr_path+"/model.onnx";
+            }
+
+            if (use_gpu_){
+                down_asr_model = down_asr_path+"/model.torchscript";
+                if (s_blade=="true" || s_blade=="True" || s_blade=="TRUE"){
+                    down_asr_model = down_asr_path+"/model_blade.torchscript";
+                }
+            }
+
+            int ret = system(python_cmd_asr.c_str());
+            if(ret !=0){
+                LOG(INFO) << "Failed to download model from modelscope. If you set local asr model path, you can ignore the errors.";
             }
 
             if (access(down_asr_model.c_str(), F_OK) != 0){
@@ -280,7 +326,7 @@
 
             if (access(s_itn_path.c_str(), F_OK) == 0) {
                 // local
-                python_cmd_itn = python_cmd + " --model-name " + s_itn_path +
+                python_cmd_itn = python_cmd + " --type onnx " + " --model-name " + s_itn_path +
                                     " --export-dir ./ " + " --model_revision " +
                                     model_path["itn-revision"] + " --export False ";
                 down_itn_path = s_itn_path;
@@ -288,7 +334,7 @@
                 // modelscope
                 LOG(INFO) << "Download model: " << s_itn_path
                             << " from modelscope : "; 
-                python_cmd_itn = python_cmd + " --model-name " +
+                python_cmd_itn = python_cmd + " --type onnx " + " --model-name " +
                         s_itn_path +
                         " --export-dir " + s_download_model_dir +
                         " --model_revision " + model_path["itn-revision"]
@@ -322,7 +368,7 @@
 
             if (access(s_lm_path.c_str(), F_OK) == 0) {
                 // local
-                python_cmd_lm = python_cmd + " --model-name " + s_lm_path +
+                python_cmd_lm = python_cmd + " --type onnx " + " --model-name " + s_lm_path +
                                     " --export-dir ./ " + " --model_revision " +
                                     model_path["lm-revision"] + " --export False ";
                 down_lm_path = s_lm_path;
@@ -330,7 +376,7 @@
                 // modelscope
                 LOG(INFO) << "Download model: " << s_lm_path
                             << " from modelscope : "; 
-                python_cmd_lm = python_cmd + " --model-name " +
+                python_cmd_lm = python_cmd + " --type onnx " + " --model-name " +
                         s_lm_path +
                         " --export-dir " + s_download_model_dir +
                         " --model_revision " + model_path["lm-revision"]
@@ -365,12 +411,12 @@
 
             if (access(s_punc_path.c_str(), F_OK) == 0){
                 // local
-                python_cmd_punc = python_cmd + " --model-name " + s_punc_path + " --export-dir ./ " + " --model_revision " + model_path["punc-revision"];
+                python_cmd_punc = python_cmd + " --type onnx " + "--quantize " + s_punc_quant + " --model-name " + s_punc_path + " --export-dir ./ " + " --model_revision " + model_path["punc-revision"];
                 down_punc_path  = s_punc_path;
             }else{
                 // modelscope
                 LOG(INFO) << "Download model: " <<  s_punc_path << " from modelscope: ";
-                python_cmd_punc = python_cmd + " --model-name " + s_punc_path + " --export-dir " + s_download_model_dir + " --model_revision " + model_path["punc-revision"];
+                python_cmd_punc = python_cmd + " --type onnx " + "--quantize " + s_punc_quant + " --model-name " + s_punc_path + " --export-dir " + s_download_model_dir + " --model_revision " + model_path["punc-revision"];
                 down_punc_path  = s_download_model_dir+"/"+s_punc_path;
             }
                 
@@ -421,7 +467,7 @@
     funasr::ExtractHws(hotword_path, hws_map_);
 
     bool is_ssl = false;
-    if (!s_certfile.empty()) {
+    if (!s_certfile.empty() && access(s_certfile.c_str(), F_OK) == 0) {
       is_ssl = true;
     }
 
@@ -436,6 +482,8 @@
 
     server server_;  // server for websocket
     wss_server wss_server_;
+    server* server = nullptr;
+    wss_server* wss_server = nullptr;
     if (is_ssl) {
       LOG(INFO)<< "SSL is opened!";
       wss_server_.init_asio(&io_server);  // init asio
@@ -444,11 +492,7 @@
 
       // list on port for accept
       wss_server_.listen(asio::ip::address::from_string(s_listen_ip), s_port);
-      WebSocketServer websocket_srv(
-          io_decoder, is_ssl, nullptr, &wss_server_, s_certfile,
-          s_keyfile);  // websocket server for asr engine
-      websocket_srv.initAsr(model_path, s_model_thread_num);  // init asr model
-
+      wss_server = &wss_server_;
     } else {
       LOG(INFO)<< "SSL is closed!";
       server_.init_asio(&io_server);  // init asio
@@ -457,12 +501,15 @@
 
       // list on port for accept
       server_.listen(asio::ip::address::from_string(s_listen_ip), s_port);
-      WebSocketServer websocket_srv(
-          io_decoder, is_ssl, &server_, nullptr, s_certfile,
-          s_keyfile);  // websocket server for asr engine
-      websocket_srv.initAsr(model_path, s_model_thread_num);  // init asr model
+      server = &server_;
     }
 
+
+    WebSocketServer websocket_srv(
+        io_decoder, is_ssl, server, wss_server, s_certfile,
+        s_keyfile);  // websocket server for asr engine
+    websocket_srv.initAsr(model_path, s_model_thread_num, use_gpu_, batch_size_);  // init asr model
+
     LOG(INFO) << "decoder-thread-num: " << s_decoder_thread_num;
     LOG(INFO) << "io-thread-num: " << s_io_thread_num;
     LOG(INFO) << "model-thread-num: " << s_model_thread_num;

--
Gitblit v1.9.1