From 3b0526e7be3565c42007313b90a018a2f8c8dff1 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 04 六月 2024 11:21:36 +0800
Subject: [PATCH] update with main (#1783)

---
 runtime/onnxruntime/bin/funasr-onnx-offline-rtf.cpp |   15 ++++++++++++---
 1 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/runtime/onnxruntime/bin/funasr-onnx-offline-rtf.cpp b/runtime/onnxruntime/bin/funasr-onnx-offline-rtf.cpp
index 5722693..c252bc7 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 < 1; i++)
+    for (size_t i = 0; i < 10; i++)
     {
         FUNASR_RESULT result=FunOfflineInfer(asr_handle, wav_list[0].c_str(), RASR_NONE, nullptr, hotwords_embedding, audio_fs, true, decoder_handle);
         if(result){
@@ -127,6 +127,7 @@
     TCLAP::CmdLine cmd("funasr-onnx-offline-rtf", ' ', "1.0");
     TCLAP::ValueArg<std::string>    model_dir("", MODEL_DIR, "the 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");
@@ -140,11 +141,14 @@
 
     TCLAP::ValueArg<std::string> wav_path("", WAV_PATH, "the input could be: wav_path, e.g.: asr_example.wav; pcm_path, e.g.: asr_example.pcm; wav.scp, kaldi style wav list (wav_id \t wav_path)", true, "", "string");
     TCLAP::ValueArg<std::int32_t>   audio_fs("", AUDIO_FS, "the sample rate of audio", false, 16000, "int32_t");
-    TCLAP::ValueArg<std::int32_t> thread_num("", THREAD_NUM, "multi-thread num for rtf", true, 0, "int32_t");
+    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);
+    cmd.add(bladedisc);
     cmd.add(vad_dir);
     cmd.add(vad_quant);
     cmd.add(punc_dir);
@@ -159,11 +163,14 @@
     cmd.add(wav_path);
     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;
     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);
@@ -175,7 +182,9 @@
 
     struct timeval start, end;
     gettimeofday(&start, nullptr);
-    FUNASR_HANDLE asr_handle=FunOfflineInit(model_path, 1);
+    bool use_gpu_ = use_gpu.getValue();
+    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