| | |
| | | #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) { |
| | |
| | | |
| | | 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) |
| | |
| | | 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"); |
| | |
| | | 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: 阿里巴巴 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); |
| | | cmd.add(bladedisc); |
| | | cmd.add(vad_dir); |
| | | cmd.add(vad_quant); |
| | | cmd.add(punc_dir); |
| | |
| | | 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; |
| | | GetValue(model_dir, MODEL_DIR, model_path); |
| | | GetValue(quantize, QUANTIZE, model_path); |
| | | GetValue(bladedisc, QUANTIZE, model_path); |
| | | GetValue(vad_dir, VAD_DIR, model_path); |
| | | GetValue(vad_quant, VAD_QUANT, model_path); |
| | | GetValue(punc_dir, PUNC_DIR, model_path); |
| | |
| | | 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(); |
| | | FUNASR_HANDLE asr_hanlde=FunOfflineInit(model_path, thread_num, use_gpu_); |
| | | |
| | | if (!asr_hanlde) |
| | | { |
| | |
| | | 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"; |
| | |
| | | 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); |
| | | |
| | |
| | | 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); |
| | | } |