From 462355c002131c105b29b8821f67f97c532b6808 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期四, 21 三月 2024 15:38:59 +0800
Subject: [PATCH] fix func FunASRWfstDecoderInit
---
runtime/onnxruntime/bin/funasr-onnx-offline.cpp | 34 ++++++++++++++++++++++++++++++++--
1 files changed, 32 insertions(+), 2 deletions(-)
diff --git a/runtime/onnxruntime/bin/funasr-onnx-offline.cpp b/runtime/onnxruntime/bin/funasr-onnx-offline.cpp
index edb83bd..988787e 100644
--- a/runtime/onnxruntime/bin/funasr-onnx-offline.cpp
+++ b/runtime/onnxruntime/bin/funasr-onnx-offline.cpp
@@ -19,6 +19,7 @@
#include "com-define.h"
#include <unordered_map>
#include "util.h"
+#include "audio.h"
using namespace std;
bool is_target_file(const std::string& filename, const std::string target) {
@@ -57,6 +58,7 @@
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::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);
cmd.add(model_dir);
cmd.add(quantize);
@@ -73,6 +75,7 @@
cmd.add(wav_path);
cmd.add(audio_fs);
cmd.add(hotword);
+ cmd.add(use_gpu);
cmd.parse(argc, argv);
std::map<std::string, std::string> model_path;
@@ -89,7 +92,8 @@
struct timeval start, end;
gettimeofday(&start, nullptr);
int thread_num = 1;
- FUNASR_HANDLE asr_hanlde=FunOfflineInit(model_path, thread_num);
+ bool use_gpu_ = use_gpu.getValue();
+ FUNASR_HANDLE asr_hanlde=FunOfflineInit(model_path, thread_num, use_gpu_);
if (!asr_hanlde)
{
@@ -156,8 +160,34 @@
for (int i = 0; i < wav_list.size(); i++) {
auto& wav_file = wav_list[i];
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;
+
gettimeofday(&start, nullptr);
- FUNASR_RESULT result=FunOfflineInfer(asr_hanlde, wav_file.c_str(), RASR_NONE, nullptr, hotwords_embedding, audio_fs.getValue(), true, decoder_handle);
+ 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);
gettimeofday(&end, nullptr);
seconds = (end.tv_sec - start.tv_sec);
taking_micros += ((seconds * 1000000) + end.tv_usec) - (start.tv_usec);
--
Gitblit v1.9.1