ttslearn.dnntts.gen.predict_duration

ttslearn.dnntts.gen.predict_duration(device, labels, duration_model, duration_config, duration_in_scaler, duration_out_scaler, binary_dict, numeric_dict)

Predict phoneme durations.

Parameters

• device (torch.device) – pytorch device

• labels (list) – list of labels

• duration_model (nn.Module) – trained duration model

• duration_config (dict) – configuration of duration model

• duration_in_scaler (sklearn.preprocessing.StandardScaler) – StandardScaler of duration features

• duration_out_scaler (sklearn.preprocessing.StandardScaler) – StandardScaler of duration output

• binary_dict (dict) – dictionary of binary features

• numeric_dict (dict) – dictionary of numeric features

Returns

predicted durations

Return type

numpy.ndarray