linter fixes and version updates for deps

TTS/bin/train_vocoder_wavegrad.py

@@ -344,7 +344,7 @@ def main(args):  # pylint: disable=redefined-outer-name
 
     # setup criterion
     criterion = torch.nn.L1Loss().cuda()
-    
+
     if use_cuda:
         model.cuda()
         criterion.cuda()

TTS/utils/audio.py

@@ -292,7 +292,7 @@ class AudioProcessor(object):
         return pad // 2, pad // 2 + pad % 2
 
     ### Compute F0 ###
-    # TODO: pw causes some dep issues 
+    # TODO: pw causes some dep issues
     # def compute_f0(self, x):
     #     f0, t = pw.dio(
     #         x.astype(np.double),

hubconf.py

@@ -1,9 +1,6 @@
 dependencies = ['torch', 'gdown']
 import torch
-import os
-import zipfile
 
-from TTS.utils.generic_utils import get_user_data_dir
 from TTS.utils.synthesizer import Synthesizer
 from TTS.utils.manage import ModelManager
 
@@ -15,7 +12,7 @@ def tts(model_name='tts_models/en/ljspeech/tacotron2-DCA', vocoder_name='vocoder
         >>> synthesizer = torch.hub.load('mozilla/TTS', 'tts', source='github')
         >>> wavs = synthesizer.tts("This is a test! This is also a test!!")
             wavs - is a list of values of the synthesized speech.
-        
+
     Args:
         model_name (str, optional): One of the model names from .model.json. Defaults to 'tts_models/en/ljspeech/tacotron2-DCA'.
         vocoder_name (str, optional): One of the model names from .model.json. Defaults to 'vocoder_models/en/ljspeech/mulitband-melgan'.
@@ -23,15 +20,15 @@ def tts(model_name='tts_models/en/ljspeech/tacotron2-DCA', vocoder_name='vocoder
 
     Returns:
         TTS.utils.synthesizer.Synthesizer: Synthesizer object wrapping both vocoder and tts models.
-    """    
+    """
     manager = ModelManager()
-  
+
     model_path, config_path = manager.download_model(model_name)
     vocoder_path, vocoder_config_path = manager.download_model(vocoder_name)
-    
+
     # create synthesizer
-    synthesizer = Synthesizer(model_path, config_path, vocoder_path, vocoder_config_path)
-    return synthesizer
+    synt = Synthesizer(model_path, config_path, vocoder_path, vocoder_config_path)
+    return synt
 
 
 if __name__ == '__main__':

pyproject.toml

@@ -1,2 +1,2 @@
 [build-system]
-requires = ["setuptools", "wheel", "Cython", "numpy>=1.16.0"]
+requires = ["setuptools", "wheel", "Cython", "numpy==1.17.0"]

requirements.txt

@@ -1,6 +1,6 @@
 torch>=1.5
 tensorflow==2.3.1
-numpy>=1.16.0
+numpy==1.17.0
 scipy>=0.19.0
 numba==0.48
 librosa==0.7.2

tests/test_vocoder_gan_datasets.py

@@ -61,7 +61,8 @@ def gan_dataset_case(batch_size, seq_len, hop_len, conv_pad, return_segments, us
                     mel = ap.melspectrogram(audio)
                     # the first 2 and the last 2 frames are skipped due to the padding
                     # differences in stft
-                    assert (feat - mel[:, :feat1.shape[-1]])[:, 2:-2].sum() <= 0, f' [!] {(feat - mel[:, :feat1.shape[-1]])[:, 2:-2].sum()}'
+                    max_diff = abs((feat - mel[:, :feat1.shape[-1]])[:, 2:-2]).max()
+                    assert max_diff <= 0, f' [!] {max_diff}'
 
             count_iter += 1
             # if count_iter == max_iter: