Fix imports

TTS/model.py

@@ -6,7 +6,6 @@ import torch
 from coqpit import Coqpit
 from torch import nn
 
-from TTS.utils.audio import AudioProcessor
 
 # pylint: skip-file
 
@@ -81,7 +80,7 @@ class BaseModel(nn.Module, ABC):
         ...
         return outputs_dict, loss_dict
 
-    def train_log(self, batch: Dict, outputs: Dict, logger: "Logger", assets: Dict, steps: int) -> None:
+    def train_log(self, batch: Dict, outputs: Dict, logger: "Logger", assets:Dict, steps:int) -> None:
         """Create visualizations and waveform examples for training.
 
         For example, here you can plot spectrograms and generate sample sample waveforms from these spectrograms to
@@ -114,7 +113,7 @@ class BaseModel(nn.Module, ABC):
         ...
         return outputs_dict, loss_dict
 
-    def eval_log(self, batch: Dict, outputs: Dict, logger: "Logger", assets: Dict, steps: int) -> None:
+    def eval_log(self, batch: Dict, outputs: Dict, logger: "Logger", assets:Dict, steps:int) -> None:
         """The same as `train_log()`"""
         pass
 

TTS/tts/datasets/formatters.py

@@ -308,14 +308,14 @@ def mls(root_path, meta_files=None):
 # ======================================== VOX CELEB ===========================================
 def voxceleb2(root_path, meta_file=None):
     """
-    :param meta_file   Used only for consistency with load_meta_data api
+    :param meta_file   Used only for consistency with load_tts_samples api
     """
     return _voxcel_x(root_path, meta_file, voxcel_idx="2")
 
 
 def voxceleb1(root_path, meta_file=None):
     """
-    :param meta_file   Used only for consistency with load_meta_data api
+    :param meta_file   Used only for consistency with load_tts_samples api
     """
     return _voxcel_x(root_path, meta_file, voxcel_idx="1")
 

TTS/tts/utils/speakers.py

@@ -110,10 +110,10 @@ class SpeakerManager:
 
     @staticmethod
     def parse_speakers_from_data(items: list) -> Tuple[Dict, int]:
-        """Parse speaker IDs from data samples retured by `load_meta_data()`.
+        """Parse speaker IDs from data samples retured by `load_tts_samples()`.
 
         Args:
-            items (list): Data sampled returned by `load_meta_data()`.
+            items (list): Data sampled returned by `load_tts_samples()`.
 
         Returns:
             Tuple[Dict, int]: speaker IDs and number of speakers.
@@ -127,7 +127,7 @@ class SpeakerManager:
         """Set speaker IDs from data samples.
 
         Args:
-            items (List): Data sampled returned by `load_meta_data()`.
+            items (List): Data sampled returned by `load_tts_samples()`.
         """
         self.speaker_ids, _ = self.parse_speakers_from_data(items)
 

TTS/vocoder/datasets/__init__.py

@@ -5,6 +5,7 @@ from torch.utils.data import Dataset
 
 from TTS.utils.audio import AudioProcessor
 from TTS.vocoder.datasets.gan_dataset import GANDataset
+from TTS.vocoder.datasets.preprocess import load_wav_data, load_wav_feat_data
 from TTS.vocoder.datasets.wavegrad_dataset import WaveGradDataset
 from TTS.vocoder.datasets.wavernn_dataset import WaveRNNDataset