This project uses a variety of advanced voiceprint recognition models such as EcapaTdnn, ResNetSE, ERes2Net, CAM++, etc. It is not excluded that more models will be supported in the future. At the same time, this project also supports MelSpectrogram, Spectrogram data preprocessing methods
[2023-05-02 14:34:01.811351 INFO ] utils:print_arguments:28 - max_epoch: 50 [2023-05-02 14:34:01.811389 INFO ] utils:print_arguments:30 - use_loss: AAMLoss [2023-05-02 14:34:01.811427 INFO ] utils:print_arguments:30 - use_model: Res2Net [2023-05-02 14:34:01.811465 INFO ] utils:print_arguments:31 - ------------------------------------------------ /home/hao/anaconda3/envs/tdnn/lib/python3.8/site-packages/torchaudio/functional/functional.py:594: UserWarning: At least one mel filterbank has all zero values. The value for
n_mels(64) may be set too high. Or, the value for
n_freqs` (513) may be set too low. warnings.warn( [2023-05-02 14:34:04.088952 INFO ] augmentation:_parse_pipeline_from:94 - 数据增强配置:{'type': 'noise', 'aug_type': 'audio', 'params': {'min_snr_dB': 10, 'max_snr_dB': 50, 'repetition': 2, 'noise_dir': 'dataset/noise/'}, 'prob': 0.0} [2023-05-02 14:34:04.089046 INFO ] augmentation:_parse_pipeline_from:94 - 数据增强配置:{'type': 'resample', 'aug_type': 'audio', 'params': {'new_sample_rate': [8000, 32000, 44100, 48000]}, 'prob': 0.0} [2023-05-02 14:34:04.089107 INFO ] augmentation:_parse_pipeline_from:94 - 数据增强配置:{'type': 'speed', 'aug_type': 'audio', 'params': {'min_speed_rate': 0.9, 'max_speed_rate': 1.1, 'num_rates': 3}, 'prob': 0.5} [2023-05-02 14:34:04.089164 INFO ] augmentation:_parse_pipeline_from:94 - 数据增强配置:{'type': 'shift', 'aug_type': 'audio', 'params': {'min_shift_ms': -5, 'max_shift_ms': 5}, 'prob': 0.0} [2023-05-02 14:34:04.089218 INFO ] augmentation:_parse_pipeline_from:94 - 数据增强配置:{'type': 'volume', 'aug_type': 'audio', 'params': {'min_gain_dBFS': -15, 'max_gain_dBFS': 15}, 'prob': 0.5} Traceback (most recent call last): File "/home/hao/VoiceprintRecognition-Pytorch-develop/train.py", line 22, inProcess finished with exit code 1`