From ade08818b7a579aac75182b906a5bd3b8126411c Mon Sep 17 00:00:00 2001
From: Yabin Li <wucong.lyb@alibaba-inc.com>
Date: 星期一, 27 五月 2024 15:46:26 +0800
Subject: [PATCH] Merge branch 'dev_batch' into main
---
runtime/websocket/bin/funasr-wss-server.cpp | 14 +++++++++++++-
1 files changed, 13 insertions(+), 1 deletions(-)
diff --git a/runtime/websocket/bin/funasr-wss-server.cpp b/runtime/websocket/bin/funasr-wss-server.cpp
index 5bb7def..100cf35 100644
--- a/runtime/websocket/bin/funasr-wss-server.cpp
+++ b/runtime/websocket/bin/funasr-wss-server.cpp
@@ -56,6 +56,10 @@
"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,
"default: /workspace/models/vad, the vad model path, which contains model_quant.onnx, vad.yaml, vad.mvn",
@@ -121,6 +125,8 @@
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);
@@ -135,6 +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);
@@ -151,11 +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);
@@ -173,6 +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{
@@ -468,7 +480,7 @@
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); // init asr model
+ 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;
--
Gitblit v1.9.1