| | |
| | | TCLAP::ValueArg<std::string> quantize("", QUANTIZE, "false (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> 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"); |
| | | |
| | | cmd.add(model_dir); |
| | | cmd.add(quantize); |
| | | cmd.add(wav_path); |
| | | cmd.add(audio_fs); |
| | | cmd.parse(argc, argv); |
| | | |
| | | std::map<std::string, std::string> model_path; |
| | |
| | | auto& wav_file = wav_list[i]; |
| | | auto& wav_id = wav_ids[i]; |
| | | |
| | | int32_t sampling_rate_ = -1; |
| | | int32_t sampling_rate_ = audio_fs.getValue(); |
| | | funasr::Audio audio(1); |
| | | if(is_target_file(wav_file.c_str(), "wav")){ |
| | | int32_t sampling_rate_ = -1; |
| | | if(!audio.LoadWav2Char(wav_file.c_str(), &sampling_rate_)){ |
| | | LOG(ERROR)<<"Failed to load "<< wav_file; |
| | | exit(-1); |
| | |
| | | is_final = false; |
| | | } |
| | | gettimeofday(&start, NULL); |
| | | FUNASR_RESULT result = FsmnVadInferBuffer(online_hanlde, speech_buff+sample_offset, step, NULL, is_final, 16000); |
| | | FUNASR_RESULT result = FsmnVadInferBuffer(online_hanlde, speech_buff+sample_offset, step, NULL, is_final, sampling_rate_); |
| | | gettimeofday(&end, NULL); |
| | | seconds = (end.tv_sec - start.tv_sec); |
| | | taking_micros += ((seconds * 1000000) + end.tv_usec) - (start.tv_usec); |