Pytorch声纹识别模型EcapaTdnn超大数据集（MelSpectrogram）

[ { "type": "noise", "aug_type": "audio", "params": { "min_snr_dB": 10, "max_snr_dB": 50, "repetition": 2, "noise_dir": "dataset/noise/" }, "prob": 0.0 }, { "type": "resample", "aug_type": "audio", "params": { "new_sample_rate": [8000, 32000, 44100, 48000] }, "prob": 0.0 }, { "type": "speed", "aug_type": "audio", "params": { "min_speed_rate": 0.9, "max_speed_rate": 1.1, "num_rates": 3 }, "prob": 0.5 }, { "type": "shift", "aug_type": "audio", "params": { "min_shift_ms": -5, "max_shift_ms": 5 }, "prob": 0.0 }, { "type": "volume", "aug_type": "audio", "params": { "min_gain_dBFS": -15, "max_gain_dBFS": 15 }, "prob": 0.5 }, { "type": "specaug", "aug_type": "feature", "params": { "inplace": true, "max_time_warp": 5, "max_t_ratio": 0.01, "n_freq_masks": 2, "max_f_ratio": 0.05, "n_time_masks": 2, "replace_with_zero": true }, "prob": 0.5 }, { "type": "specsub", "aug_type": "feature", "params": { "max_t": 10, "num_t_sub": 2 }, "prob": 0.0 } ]