nnsvs.gen.predict_timelag

nnsvs.gen.predict_timelag(device, labels, timelag_model, timelag_config, timelag_in_scaler, timelag_out_scaler, binary_dict, numeric_dict, pitch_indices=None, log_f0_conditioning=True, allowed_range=None, allowed_range_rest=None, force_clip_input_features=False, frame_period=5)[source]

Predict time-lag from HTS labels

Parameters:

  • device (torch.device) – device

  • labels (nnmnkwii.io.hts.HTSLabelFile) – HTS-style labels

  • timelag_model (nn.Module) – time-lag model

  • timelag_config (dict) – time-lag model config

  • timelag_in_scaler (sklearn.preprocessing.MinMaxScaler) – input scaler

  • timelag_out_scaler (sklearn.preprocessing.MinMaxScaler) – output scaler

  • binary_dict (dict) – binary feature dict

  • numeric_dict (dict) – numeric feature dict

  • pitch_indices (list) – indices of pitch features

  • log_f0_conditioning (bool) – whether to condition on log f0

  • allowed_range (list) – allowed range of time-lag

  • allowed_range_rest (list) – allowed range of time-lag for rest

  • force_clip_input_features (bool) – whether to clip input features

Returns;

ndarray: time-lag predictions