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