mass linter fix

tests/generic_utils_text.py

@@ -1,35 +0,0 @@
-import unittest
-import torch as T
-
-from mozilla_voice_tts.tts.utils.generic_utils import save_checkpoint, save_best_model
-from mozilla_voice_tts.tts.layers.tacotron import Prenet
-
-OUT_PATH = '/tmp/test.pth.tar'
-
-
-class ModelSavingTests(unittest.TestCase):
-    def save_checkpoint_test(self):
-        # create a dummy model
-        model = Prenet(128, out_features=[256, 128])
-        model = T.nn.DataParallel(layer) #FIXME: undefined variable layer
-
-        # save the model
-        save_checkpoint(model, None, 100, OUT_PATH, 1, 1)
-
-        # load the model to CPU
-        model_dict = T.load(
-            MODEL_PATH, map_location=lambda storage, loc: storage) #FIXME: undefined variable MODEL_PATH
-        model.load_state_dict(model_dict['model'])
-
-    def save_best_model_test(self):
-        # create a dummy model
-        model = Prenet(256, out_features=[256, 256])
-        model = T.nn.DataParallel(layer)
-
-        # save the model
-        save_best_model(model, None, 0, 100, OUT_PATH, 10, 1)
-
-        # load the model to CPU
-        model_dict = T.load(
-            MODEL_PATH, map_location=lambda storage, loc: storage)
-        model.load_state_dict(model_dict['model'])

tests/test_audio.py

@@ -1,7 +1,8 @@
 import os
 import unittest
 
-from tests import get_tests_path, get_tests_input_path, get_tests_output_path
+from tests import get_tests_input_path, get_tests_output_path, get_tests_path
+
 from mozilla_voice_tts.utils.audio import AudioProcessor
 from mozilla_voice_tts.utils.io import load_config
 
@@ -103,7 +104,7 @@ class TestAudio(unittest.TestCase):
         assert (x_old - x).sum() == 0
         # check value range
         assert x_norm.max() <= self.ap.max_norm + 1, x_norm.max()
-        assert x_norm.min() >= -self.ap.max_norm - 2, x_norm.min()
+        assert x_norm.min() >= -self.ap.max_norm - 2, x_norm.min()  #pylint: disable=invalid-unary-operand-type
         assert x_norm.min() <= 0, x_norm.min()
         # check denorm.
         x_ = self.ap._denormalize(x_norm)
@@ -120,7 +121,7 @@ class TestAudio(unittest.TestCase):
         assert (x_old - x).sum() == 0
         # check value range
         assert x_norm.max() <= self.ap.max_norm, x_norm.max()
-        assert x_norm.min() >= -self.ap.max_norm, x_norm.min()
+        assert x_norm.min() >= -self.ap.max_norm, x_norm.min()  #pylint: disable=invalid-unary-operand-type
         assert x_norm.min() <= 0, x_norm.min()
         # check denorm.
         x_ = self.ap._denormalize(x_norm)
@@ -148,7 +149,7 @@ class TestAudio(unittest.TestCase):
 
         assert (x_old - x).sum() == 0
         assert x_norm.max() <= self.ap.max_norm, x_norm.max()
-        assert x_norm.min() >= -self.ap.max_norm, x_norm.min()
+        assert x_norm.min() >= -self.ap.max_norm, x_norm.min()  #pylint: disable=invalid-unary-operand-type
         assert x_norm.min() < 0, x_norm.min()
         x_ = self.ap._denormalize(x_norm)
         assert (x - x_).sum() < 1e-3

tests/test_demo_server.py

@@ -1,13 +1,13 @@
 import os
 import unittest
 
-import torch as T
+from tests import get_tests_input_path, get_tests_output_path
 
 from mozilla_voice_tts.server.synthesizer import Synthesizer
-from tests import get_tests_input_path, get_tests_output_path
-from mozilla_voice_tts.tts.utils.text.symbols import make_symbols, phonemes, symbols
 from mozilla_voice_tts.tts.utils.generic_utils import setup_model
 from mozilla_voice_tts.tts.utils.io import save_checkpoint
+from mozilla_voice_tts.tts.utils.text.symbols import (make_symbols, phonemes,
+                                                      symbols)
 from mozilla_voice_tts.utils.io import load_config
 
 

tests/test_encoder.py

@@ -1,13 +1,13 @@
 import os
 import unittest
+
 import torch as T
+from tests import get_tests_input_path
 
-from tests import get_tests_path, get_tests_input_path
-from mozilla_voice_tts.speaker_encoder.model import SpeakerEncoder
 from mozilla_voice_tts.speaker_encoder.loss import GE2ELoss
+from mozilla_voice_tts.speaker_encoder.model import SpeakerEncoder
 from mozilla_voice_tts.utils.io import load_config
 
-
 file_path = get_tests_input_path()
 c = load_config(os.path.join(file_path, "test_config.json"))
 

tests/test_layers.py

@@ -9,7 +9,7 @@ from mozilla_voice_tts.tts.utils.generic_utils import sequence_mask
 
 
 class PrenetTests(unittest.TestCase):
-    def test_in_out(self):
+    def test_in_out(self):  #pylint: disable=no-self-use
         layer = Prenet(128, out_features=[256, 128])
         dummy_input = T.rand(4, 128)
 
@@ -104,7 +104,7 @@ class DecoderTests(unittest.TestCase):
 
 
 class EncoderTests(unittest.TestCase):
-    def test_in_out(self):
+    def test_in_out(self):  #pylint: disable=no-self-use
         layer = Encoder(128)
         dummy_input = T.rand(4, 8, 128)
 
@@ -117,7 +117,7 @@ class EncoderTests(unittest.TestCase):
 
 
 class L1LossMaskedTests(unittest.TestCase):
-    def test_in_out(self):
+    def test_in_out(self):  #pylint: disable=no-self-use
         # test input == target
         layer = L1LossMasked(seq_len_norm=False)
         dummy_input = T.ones(4, 8, 128).float()

tests/test_loader.py

@@ -1,15 +1,16 @@
 import os
-import unittest
 import shutil
-import torch
-import numpy as np
+import unittest
 
-from tests import get_tests_path, get_tests_input_path, get_tests_output_path
+import numpy as np
+import torch
+from tests import get_tests_input_path, get_tests_output_path
 from torch.utils.data import DataLoader
-from mozilla_voice_tts.utils.io import load_config
-from mozilla_voice_tts.utils.audio import AudioProcessor
+
 from mozilla_voice_tts.tts.datasets import TTSDataset
 from mozilla_voice_tts.tts.datasets.preprocess import ljspeech
+from mozilla_voice_tts.utils.audio import AudioProcessor
+from mozilla_voice_tts.utils.io import load_config
 
 #pylint: disable=unused-variable
 
@@ -32,7 +33,7 @@ class TestTTSDataset(unittest.TestCase):
         self.ap = AudioProcessor(**c.audio)
 
     def _create_dataloader(self, batch_size, r, bgs):
-        items = ljspeech(c.data_path,'metadata.csv')
+        items = ljspeech(c.data_path, 'metadata.csv')
         dataset = TTSDataset.MyDataset(
             r,
             c.text_cleaner,
@@ -74,7 +75,7 @@ class TestTTSDataset(unittest.TestCase):
                 assert check_count == 0, \
                     " !! Negative values in text_input: {}".format(check_count)
                 # TODO: more assertion here
-                assert type(speaker_name[0]) is str
+                assert isinstance(speaker_name[0], str)
                 assert linear_input.shape[0] == c.batch_size
                 assert linear_input.shape[2] == self.ap.fft_size // 2 + 1
                 assert mel_input.shape[0] == c.batch_size
@@ -82,7 +83,7 @@ class TestTTSDataset(unittest.TestCase):
                 # check normalization ranges
                 if self.ap.symmetric_norm:
                     assert mel_input.max() <= self.ap.max_norm
-                    assert mel_input.min() >= -self.ap.max_norm
+                    assert mel_input.min() >= -self.ap.max_norm  #pylint: disable=invalid-unary-operand-type
                     assert mel_input.min() < 0
                 else:
                     assert mel_input.max() <= self.ap.max_norm

tests/test_preprocessors.py

@@ -7,7 +7,7 @@ from mozilla_voice_tts.tts.datasets.preprocess import common_voice
 
 class TestPreprocessors(unittest.TestCase):
 
-    def test_common_voice_preprocessor(self):
+    def test_common_voice_preprocessor(self):  #pylint: disable=no-self-use
         root_path = get_tests_input_path()
         meta_file = "common_voice.tsv"
         items = common_voice(root_path, meta_file)

tests/test_tacotron2_model.py

@@ -20,8 +20,8 @@ c = load_config(os.path.join(get_tests_input_path(), 'test_config.json'))
 
 
 class TacotronTrainTest(unittest.TestCase):
-    def test_train_step(self):
-        input = torch.randint(0, 24, (8, 128)).long().to(device)
+    def test_train_step(self):  # pylint: disable=no-self-use
+        input_dummy = torch.randint(0, 24, (8, 128)).long().to(device)
         input_lengths = torch.randint(100, 128, (8, )).long().to(device)
         input_lengths = torch.sort(input_lengths, descending=True)[0]
         mel_spec = torch.rand(8, 30, c.audio['num_mels']).to(device)
@@ -34,7 +34,7 @@ class TacotronTrainTest(unittest.TestCase):
         for idx in mel_lengths:
             stop_targets[:, int(idx.item()):, 0] = 1.0
 
-        stop_targets = stop_targets.view(input.shape[0],
+        stop_targets = stop_targets.view(input_dummy.shape[0],
                                          stop_targets.size(1) // c.r, -1)
         stop_targets = (stop_targets.sum(2) > 0.0).unsqueeze(2).float().squeeze()
 
@@ -51,7 +51,7 @@ class TacotronTrainTest(unittest.TestCase):
         optimizer = optim.Adam(model.parameters(), lr=c.lr)
         for i in range(5):
             mel_out, mel_postnet_out, align, stop_tokens = model.forward(
-                input, input_lengths, mel_spec, mel_lengths, speaker_ids)
+                input_dummy, input_lengths, mel_spec, mel_lengths, speaker_ids)
             assert torch.sigmoid(stop_tokens).data.max() <= 1.0
             assert torch.sigmoid(stop_tokens).data.min() >= 0.0
             optimizer.zero_grad()

tests/test_tacotron2_tf_model.py

@@ -1,15 +1,19 @@
 import os
-import torch
 import unittest
+
 import numpy as np
 import tensorflow as tf
+import torch
+from tests import get_tests_input_path
+
+from mozilla_voice_tts.tts.tf.models.tacotron2 import Tacotron2
+from mozilla_voice_tts.tts.tf.utils.tflite import (convert_tacotron2_to_tflite,
+                                                   load_tflite_model)
+from mozilla_voice_tts.utils.io import load_config
+
 tf.get_logger().setLevel('INFO')
 
-from tests import get_tests_path, get_tests_input_path, get_tests_output_path
 
-from mozilla_voice_tts.utils.io import load_config
-from mozilla_voice_tts.tts.tf.models.tacotron2 import Tacotron2
-from mozilla_voice_tts.tts.tf.utils.tflite import convert_tacotron2_to_tflite, load_tflite_model
 
 #pylint: disable=unused-variable
 
@@ -132,4 +136,3 @@ class TacotronTFTrainTest(unittest.TestCase):
         postnet_output = tflite_model.get_tensor(output_details[1]['index'])
         # remove tflite binary
         os.remove('test_tacotron2.tflite')
-

tests/test_text_processing.py

@@ -16,7 +16,7 @@ def test_phoneme_to_sequence():
     lang = "en-us"
     sequence = phoneme_to_sequence(text, text_cleaner, lang)
     text_hat = sequence_to_phoneme(sequence)
-    sequence_with_params = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
+    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
     text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters)
     gt = "ɹiːsənt ɹɪsɜːtʃ æt hɑːɹvɚd hɐz ʃoʊn mɛdᵻteɪɾɪŋ fɔːɹ æz lɪɾəl æz eɪt wiːks kæn æktʃuːəli ɪnkɹiːs, ðə ɡɹeɪ mæɾɚɹ ɪnðə pɑːɹts ʌvðə bɹeɪn ɹɪspɑːnsəbəl fɔːɹ ɪmoʊʃənəl ɹɛɡjuːleɪʃən ænd lɜːnɪŋ!"
     assert text_hat == text_hat_with_params == gt
@@ -25,7 +25,7 @@ def test_phoneme_to_sequence():
     text = "Be a voice, not an! echo?"
     sequence = phoneme_to_sequence(text, text_cleaner, lang)
     text_hat = sequence_to_phoneme(sequence)
-    sequence_with_params = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
+    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
     text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters)
     gt = "biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ?"
     print(text_hat)
@@ -36,7 +36,7 @@ def test_phoneme_to_sequence():
     text = "Be a voice, not an! echo"
     sequence = phoneme_to_sequence(text, text_cleaner, lang)
     text_hat = sequence_to_phoneme(sequence)
-    sequence_with_params = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
+    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
     text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters)
     gt = "biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ"
     print(text_hat)
@@ -47,7 +47,7 @@ def test_phoneme_to_sequence():
     text = "Be a voice, not an echo!"
     sequence = phoneme_to_sequence(text, text_cleaner, lang)
     text_hat = sequence_to_phoneme(sequence)
-    sequence_with_params = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
+    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
     text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters)
     gt = "biː ɐ vɔɪs, nɑːt ɐn ɛkoʊ!"
     print(text_hat)
@@ -58,7 +58,7 @@ def test_phoneme_to_sequence():
     text = "Be a voice, not an! echo.  "
     sequence = phoneme_to_sequence(text, text_cleaner, lang)
     text_hat = sequence_to_phoneme(sequence)
-    sequence_with_params = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
+    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
     text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters)
     gt = "biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ."
     print(text_hat)
@@ -69,7 +69,7 @@ def test_phoneme_to_sequence():
     text = "Be a voice, not an! echo.  "
     sequence = phoneme_to_sequence(text, text_cleaner, lang, True)
     text_hat = sequence_to_phoneme(sequence)
-    sequence_with_params = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
+    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
     text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters)
     gt = "^biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ.~"
     print(text_hat)
@@ -80,7 +80,7 @@ def test_phoneme_to_sequence():
     text = "_Be a _voice, not an! echo_"
     sequence = phoneme_to_sequence(text, text_cleaner, lang)
     text_hat = sequence_to_phoneme(sequence)
-    sequence_with_params = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
+    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
     text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters)
     gt = "biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ"
     print(text_hat)

tests/test_vocoder_melgan_discriminator.py

@@ -23,4 +23,4 @@ def test_melgan_multi_scale_discriminator():
     assert np.all(scores[0].shape == (4, 1, 64))
     assert np.all(feats[0][0].shape == (4, 16, 4096))
     assert np.all(feats[0][1].shape == (4, 64, 1024))
-    assert np.all(feats[0][2].shape == (4, 256, 256))
+    assert np.all(feats[0][2].shape == (4, 256, 256))

tests/test_vocoder_melgan_generator.py

@@ -11,4 +11,3 @@ def test_melgan_generator():
     assert np.all(output.shape == (4, 1, 64 * 256))
     output = model.inference(dummy_input)
     assert np.all(output.shape == (4, 1, (64 + 4) * 256))
-

tests/test_vocoder_pqmf.py

@@ -25,4 +25,3 @@ def test_pqmf():
     print(w2_.min())
     print(w2_.mean())
     sf.write('pqmf_output.wav', w2_.flatten().detach(), sr)
-

tests/test_vocoder_tf_pqmf.py

@@ -26,4 +26,3 @@ def test_pqmf():
     print(w2_.min())
     print(w2_.mean())
     sf.write('tf_pqmf_output.wav', w2_.flatten(), sr)
-