| | |
| | | #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) { |
| | |
| | | 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> 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); |
| | | 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); |
| | |
| | | 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); |
| | |
| | | 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(); |
| | | int batch_size_ = batch_size.getValue(); |
| | | FUNASR_HANDLE asr_hanlde=FunOfflineInit(model_path, thread_num, use_gpu_, batch_size_); |
| | | |
| | | if (!asr_hanlde) |
| | | { |
| | |
| | | for (int i = 0; i < wav_list.size(); i++) { |
| | | auto& wav_file = wav_list[i]; |
| | | auto& wav_id = wav_ids[i]; |
| | | gettimeofday(&start, nullptr); |
| | | |
| | | // 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); |