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.cpp | 54 ++++++++++++++++++++++++++++++------------------------
1 files changed, 30 insertions(+), 24 deletions(-)
diff --git a/runtime/onnxruntime/bin/funasr-onnx-offline.cpp b/runtime/onnxruntime/bin/funasr-onnx-offline.cpp
index 988787e..87928f5 100644
--- a/runtime/onnxruntime/bin/funasr-onnx-offline.cpp
+++ b/runtime/onnxruntime/bin/funasr-onnx-offline.cpp
@@ -45,6 +45,7 @@
TCLAP::CmdLine cmd("funasr-onnx-offline", ' ', "1.0");
TCLAP::ValueArg<std::string> model_dir("", MODEL_DIR, "the asr model path, which contains model.onnx, config.yaml, am.mvn", true, "", "string");
TCLAP::ValueArg<std::string> quantize("", QUANTIZE, "true (Default), load the model of model.onnx in model_dir. If set true, load the model of model_quant.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, "the vad model path, which contains model.onnx, vad.yaml, vad.mvn", false, "", "string");
TCLAP::ValueArg<std::string> vad_quant("", VAD_QUANT, "true (Default), load the model of model.onnx in vad_dir. If set true, load the model of model_quant.onnx in vad_dir", false, "true", "string");
TCLAP::ValueArg<std::string> punc_dir("", PUNC_DIR, "the punc model path, which contains model.onnx, punc.yaml", false, "", "string");
@@ -59,9 +60,11 @@
TCLAP::ValueArg<std::int32_t> audio_fs("", AUDIO_FS, "the sample rate of audio", false, 16000, "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);
+ cmd.add(bladedisc);
cmd.add(vad_dir);
cmd.add(vad_quant);
cmd.add(punc_dir);
@@ -76,11 +79,13 @@
cmd.add(audio_fs);
cmd.add(hotword);
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);
@@ -93,7 +98,8 @@
gettimeofday(&start, nullptr);
int thread_num = 1;
bool use_gpu_ = use_gpu.getValue();
- FUNASR_HANDLE asr_hanlde=FunOfflineInit(model_path, thread_num, use_gpu_);
+ int batch_size_ = batch_size.getValue();
+ FUNASR_HANDLE asr_hanlde=FunOfflineInit(model_path, thread_num, use_gpu_, batch_size_);
if (!asr_hanlde)
{
@@ -162,32 +168,32 @@
auto& wav_id = wav_ids[i];
// For debug:begin
- int32_t sampling_rate_ = audio_fs.getValue();
- funasr::Audio audio(1);
- if(is_target_file(wav_file.c_str(), "wav")){
- if(!audio.LoadWav2Char(wav_file.c_str(), &sampling_rate_)){
- LOG(ERROR)<<"Failed to load "<< wav_file;
- exit(-1);
- }
- }else if(is_target_file(wav_file.c_str(), "pcm")){
- if (!audio.LoadPcmwav2Char(wav_file.c_str(), &sampling_rate_)){
- LOG(ERROR)<<"Failed to load "<< wav_file;
- exit(-1);
- }
- }else{
- if (!audio.FfmpegLoad(wav_file.c_str(), true)){
- LOG(ERROR)<<"Failed to load "<< wav_file;
- exit(-1);
- }
- }
- char* speech_buff = audio.GetSpeechChar();
- int buff_len = audio.GetSpeechLen()*2;
+ // int32_t sampling_rate_ = audio_fs.getValue();
+ // funasr::Audio audio(1);
+ // if(is_target_file(wav_file.c_str(), "wav")){
+ // if(!audio.LoadWav2Char(wav_file.c_str(), &sampling_rate_)){
+ // LOG(ERROR)<<"Failed to load "<< wav_file;
+ // exit(-1);
+ // }
+ // }else if(is_target_file(wav_file.c_str(), "pcm")){
+ // if (!audio.LoadPcmwav2Char(wav_file.c_str(), &sampling_rate_)){
+ // LOG(ERROR)<<"Failed to load "<< wav_file;
+ // exit(-1);
+ // }
+ // }else{
+ // if (!audio.FfmpegLoad(wav_file.c_str(), true)){
+ // LOG(ERROR)<<"Failed to load "<< wav_file;
+ // exit(-1);
+ // }
+ // }
+ // char* speech_buff = audio.GetSpeechChar();
+ // int buff_len = audio.GetSpeechLen()*2;
- gettimeofday(&start, nullptr);
- FUNASR_RESULT result=FunOfflineInferBuffer(asr_hanlde, speech_buff, buff_len, RASR_NONE, nullptr, hotwords_embedding, audio_fs.getValue(), "pcm", true, decoder_handle);
+ // gettimeofday(&start, nullptr);
+ // FUNASR_RESULT result=FunOfflineInferBuffer(asr_hanlde, speech_buff, buff_len, RASR_NONE, nullptr, hotwords_embedding, audio_fs.getValue(), "pcm", true, decoder_handle);
// For debug:end
- // FUNASR_RESULT result=FunOfflineInfer(asr_hanlde, wav_file.c_str(), RASR_NONE, nullptr, hotwords_embedding, audio_fs.getValue(), true, decoder_handle);
+ FUNASR_RESULT result=FunOfflineInfer(asr_hanlde, wav_file.c_str(), RASR_NONE, nullptr, hotwords_embedding, audio_fs.getValue(), true, decoder_handle);
gettimeofday(&end, nullptr);
seconds = (end.tv_sec - start.tv_sec);
taking_micros += ((seconds * 1000000) + end.tv_usec) - (start.tv_usec);
--
Gitblit v1.9.1