update sequence_mask import globally

TTS/tts/layers/glow_tts/encoder.py

@@ -9,7 +9,7 @@ from TTS.tts.layers.generic.time_depth_sep_conv import TimeDepthSeparableConvBlo
 from TTS.tts.layers.glow_tts.duration_predictor import DurationPredictor
 from TTS.tts.layers.glow_tts.glow import ResidualConv1dLayerNormBlock
 from TTS.tts.layers.glow_tts.transformer import RelativePositionTransformer
-from TTS.tts.utils.generic_utils import sequence_mask
+from TTS.tts.utils.data import sequence_mask
 
 
 class Encoder(nn.Module):

TTS/tts/layers/glow_tts/monotonic_align/__init__.py

@@ -2,7 +2,7 @@ import numpy as np
 import torch
 from torch.nn import functional as F
 
-from TTS.tts.utils.generic_utils import sequence_mask
+from TTS.tts.utils.data import sequence_mask
 
 try:
     # TODO: fix pypi cython installation problem.

TTS/tts/models/align_tts.py

@@ -7,7 +7,7 @@ from TTS.tts.layers.feed_forward.duration_predictor import DurationPredictor
 from TTS.tts.layers.feed_forward.encoder import Encoder
 from TTS.tts.layers.generic.pos_encoding import PositionalEncoding
 from TTS.tts.layers.glow_tts.monotonic_align import generate_path, maximum_path
-from TTS.tts.utils.generic_utils import sequence_mask
+from TTS.tts.utils.data import sequence_mask
 
 
 class AlignTTS(nn.Module):

TTS/tts/models/glow_tts.py

@@ -6,8 +6,11 @@ from torch.nn import functional as F
 
 from TTS.tts.layers.glow_tts.decoder import Decoder
 from TTS.tts.layers.glow_tts.encoder import Encoder
+from TTS.tts.utils.measures import alignment_diagonal_score
+from TTS.tts.utils.visual import plot_alignment, plot_spectrogram
+from TTS.utils.audio import AudioProcessor
 from TTS.tts.layers.glow_tts.monotonic_align import generate_path, maximum_path
-from TTS.tts.utils.generic_utils import sequence_mask
+from TTS.tts.utils.data import sequence_mask
 
 
 class GlowTTS(nn.Module):

TTS/tts/models/speedy_speech.py

@@ -6,7 +6,7 @@ from TTS.tts.layers.feed_forward.duration_predictor import DurationPredictor
 from TTS.tts.layers.feed_forward.encoder import Encoder
 from TTS.tts.layers.generic.pos_encoding import PositionalEncoding
 from TTS.tts.layers.glow_tts.monotonic_align import generate_path
-from TTS.tts.utils.generic_utils import sequence_mask
+from TTS.tts.utils.data import sequence_mask
 
 
 class SpeedySpeech(nn.Module):

tests/tts_tests/test_feed_forward_layers.py

@@ -2,7 +2,7 @@ import torch
 
 from TTS.tts.layers.feed_forward.decoder import Decoder
 from TTS.tts.layers.feed_forward.encoder import Encoder
-from TTS.tts.utils.generic_utils import sequence_mask
+from TTS.tts.utils.data import sequence_mask
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 

tests/tts_tests/test_speedy_speech_layers.py

@@ -2,7 +2,7 @@ import torch
 
 from TTS.tts.layers.feed_forward.duration_predictor import DurationPredictor
 from TTS.tts.models.speedy_speech import SpeedySpeech
-from TTS.tts.utils.generic_utils import sequence_mask
+from TTS.tts.utils.data import sequence_mask
 
 use_cuda = torch.cuda.is_available()
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

tests/tts_tests/test_tacotron_layers.py

@@ -4,7 +4,7 @@ import torch as T
 
 from TTS.tts.layers.losses import L1LossMasked, SSIMLoss
 from TTS.tts.layers.tacotron.tacotron import CBHG, Decoder, Encoder, Prenet
-from TTS.tts.utils.generic_utils import sequence_mask
+from TTS.tts.utils.data import sequence_mask
 
 # pylint: disable=unused-variable