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/onnxruntime/bin/funasr-onnx-offline-rtf.cpp | 7 +++++--
1 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/runtime/onnxruntime/bin/funasr-onnx-offline-rtf.cpp b/runtime/onnxruntime/bin/funasr-onnx-offline-rtf.cpp
index 8afa77a..d8d9473 100644
--- a/runtime/onnxruntime/bin/funasr-onnx-offline-rtf.cpp
+++ b/runtime/onnxruntime/bin/funasr-onnx-offline-rtf.cpp
@@ -52,7 +52,7 @@
std::vector<std::vector<float>> hotwords_embedding = CompileHotwordEmbedding(asr_handle, nn_hotwords_);
// warm up
- for (size_t i = 0; i < 10; i++)
+ for (size_t i = 0; i < 1; i++)
{
FUNASR_RESULT result=FunOfflineInfer(asr_handle, wav_list[0].c_str(), RASR_NONE, nullptr, hotwords_embedding, audio_fs, true, decoder_handle);
if(result){
@@ -144,6 +144,7 @@
TCLAP::ValueArg<std::int32_t> thread_num("", THREAD_NUM, "multi-thread num for rtf", false, 1, "int32_t");
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, "", "string");
TCLAP::SwitchArg use_gpu("", INFER_GPU, "Whether to use GPU for inference, default is false", false);
+ TCLAP::ValueArg<std::int32_t> batch_size("", BATCHSIZE, "batch_size for ASR model when using GPU", false, 4, "int32_t");
cmd.add(model_dir);
cmd.add(quantize);
@@ -163,6 +164,7 @@
cmd.add(audio_fs);
cmd.add(thread_num);
cmd.add(use_gpu);
+ cmd.add(batch_size);
cmd.parse(argc, argv);
std::map<std::string, std::string> model_path;
@@ -181,7 +183,8 @@
struct timeval start, end;
gettimeofday(&start, nullptr);
bool use_gpu_ = use_gpu.getValue();
- FUNASR_HANDLE asr_handle=FunOfflineInit(model_path, 1, use_gpu_);
+ int batch_size_ = batch_size.getValue();
+ FUNASR_HANDLE asr_handle=FunOfflineInit(model_path, 1, use_gpu_, batch_size_);
if (!asr_handle)
{
--
Gitblit v1.9.1