From 1596f6f414f6f41da66506debb1dff19fffeb3ec Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 24 六月 2024 11:55:17 +0800
Subject: [PATCH] fixbug hotwords
---
runtime/onnxruntime/bin/funasr-onnx-offline.cpp | 60 +++++++++++++++++++++++++++++++++++++++++++++++++-----------
1 files changed, 49 insertions(+), 11 deletions(-)
diff --git a/runtime/onnxruntime/bin/funasr-onnx-offline.cpp b/runtime/onnxruntime/bin/funasr-onnx-offline.cpp
index eb908d8..87928f5 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) {
@@ -32,10 +33,8 @@
void GetValue(TCLAP::ValueArg<std::string>& value_arg, string key, std::map<std::string, std::string>& model_path)
{
- if (value_arg.isSet()){
- model_path.insert({key, value_arg.getValue()});
- LOG(INFO)<< key << " : " << value_arg.getValue();
- }
+ model_path.insert({key, value_arg.getValue()});
+ LOG(INFO)<< key << " : " << value_arg.getValue();
}
int main(int argc, char** argv)
@@ -46,11 +45,12 @@
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");
TCLAP::ValueArg<std::string> punc_quant("", PUNC_QUANT, "true (Default), load the model of model.onnx in punc_dir. If set true, load the model of model_quant.onnx in punc_dir", false, "true", "string");
- TCLAP::ValueArg<std::string> lm_dir("", LM_DIR, "the lm model path, which contains compiled models: TLG.fst, config.yaml ", false, "", "string");
+ TCLAP::ValueArg<std::string> lm_dir("", LM_DIR, "the lm model path, which contains compiled models: TLG.fst, config.yaml, lexicon.txt ", false, "", "string");
TCLAP::ValueArg<float> global_beam("", GLOB_BEAM, "the decoding beam for beam searching ", false, 3.0, "float");
TCLAP::ValueArg<float> lattice_beam("", LAT_BEAM, "the lattice generation beam for beam searching ", false, 3.0, "float");
TCLAP::ValueArg<float> am_scale("", AM_SCALE, "the acoustic scale for beam searching ", false, 10.0, "float");
@@ -59,9 +59,12 @@
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);
+ 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);
@@ -75,11 +78,14 @@
cmd.add(wav_path);
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);
@@ -89,9 +95,11 @@
GetValue(wav_path, WAV_PATH, model_path);
struct timeval start, end;
- gettimeofday(&start, NULL);
+ gettimeofday(&start, nullptr);
int thread_num = 1;
- FUNASR_HANDLE asr_hanlde=FunOfflineInit(model_path, thread_num);
+ bool use_gpu_ = use_gpu.getValue();
+ int batch_size_ = batch_size.getValue();
+ FUNASR_HANDLE asr_hanlde=FunOfflineInit(model_path, thread_num, use_gpu_, batch_size_);
if (!asr_hanlde)
{
@@ -116,7 +124,7 @@
LOG(INFO) << "hotword path: " << hotword_path;
funasr::ExtractHws(hotword_path, hws_map, nn_hotwords_);
- gettimeofday(&end, NULL);
+ gettimeofday(&end, nullptr);
long seconds = (end.tv_sec - start.tv_sec);
long modle_init_micros = ((seconds * 1000000) + end.tv_usec) - (start.tv_usec);
LOG(INFO) << "Model initialization takes " << (double)modle_init_micros / 1000000 << " s";
@@ -158,9 +166,35 @@
for (int i = 0; i < wav_list.size(); i++) {
auto& wav_file = wav_list[i];
auto& wav_id = wav_ids[i];
- gettimeofday(&start, NULL);
- FUNASR_RESULT result=FunOfflineInfer(asr_hanlde, wav_file.c_str(), RASR_NONE, NULL, hotwords_embedding, audio_fs.getValue(), true, decoder_handle);
- gettimeofday(&end, NULL);
+
+ // 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=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);
@@ -172,6 +206,10 @@
if(stamp !=""){
LOG(INFO)<< wav_id <<" : "<<stamp;
}
+ string stamp_sents = FunASRGetStampSents(result);
+ if(stamp_sents !=""){
+ LOG(INFO)<< wav_id <<" : "<<stamp_sents;
+ }
snippet_time += FunASRGetRetSnippetTime(result);
FunASRFreeResult(result);
}
--
Gitblit v1.9.1