rebranding and replacing import statements

tests/generic_utils_text.py

@@ -1,8 +1,8 @@
 import unittest
 import torch as T
 
-from TTS.tts.utils.generic_utils import save_checkpoint, save_best_model
-from TTS.tts.layers.tacotron import Prenet
+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'
 

tests/inputs/test_train_config.json

@@ -67,6 +67,7 @@
     "gradual_training": [[0, 7, 4]], //set gradual training steps [first_step, r, batch_size]. If it is null, gradual training is disabled. For Tacotron, you might need to reduce the 'batch_size' as you proceeed.
     "loss_masking": true,         // enable / disable loss masking against the sequence padding.
     "ga_alpha": 10.0,        // weight for guided attention loss. If > 0, guided attention is enabled.
+    "apex_amp_level": null,
 
     // VALIDATION
     "run_eval": true,

tests/outputs/dummy_model_config.json

@@ -73,7 +73,7 @@
     "data_path": "/media/erogol/data_ssd/Data/Mozilla/",  // DATASET-RELATED: can overwritten from command argument
     "meta_file_train": "metadata_train.txt",      // DATASET-RELATED: metafile for training dataloader.
     "meta_file_val": "metadata_val.txt",    // DATASET-RELATED: metafile for evaluation dataloader.
-    "dataset": "mozilla",      // DATASET-RELATED: one of TTS.dataset.preprocessors depending on your target dataset. Use "tts_cache" for pre-computed dataset by extract_features.py
+    "dataset": "mozilla",      // DATASET-RELATED: one of mozilla_voice_tts.dataset.preprocessors depending on your target dataset. Use "tts_cache" for pre-computed dataset by extract_features.py
     "min_seq_len": 0,       // DATASET-RELATED: minimum text length to use in training
     "max_seq_len": 150,     // DATASET-RELATED: maximum text length
     "output_path": "../keep/",      // DATASET-RELATED: output path for all training outputs.

tests/symbols_tests.py

@@ -1,6 +1,6 @@
 import unittest
 
-from TTS.tts.utils.text import phonemes
+from mozilla_voice_tts.tts.utils.text import phonemes
 
 class SymbolsTest(unittest.TestCase):
     def test_uniqueness(self):  #pylint: disable=no-self-use

tests/test_audio.py

@@ -2,8 +2,8 @@ import os
 import unittest
 
 from tests import get_tests_path, get_tests_input_path, get_tests_output_path
-from TTS.utils.audio import AudioProcessor
-from TTS.utils.io import load_config
+from mozilla_voice_tts.utils.audio import AudioProcessor
+from mozilla_voice_tts.utils.io import load_config
 
 TESTS_PATH = get_tests_path()
 OUT_PATH = os.path.join(get_tests_output_path(), "audio_tests")

tests/test_demo_server.py

@@ -3,12 +3,12 @@ import unittest
 
 import torch as T
 
-from TTS.server.synthesizer import Synthesizer
+from mozilla_voice_tts.server.synthesizer import Synthesizer
 from tests import get_tests_input_path, get_tests_output_path
-from TTS.tts.utils.text.symbols import make_symbols, phonemes, symbols
-from TTS.tts.utils.generic_utils import setup_model
-from TTS.tts.utils.io import save_checkpoint
-from TTS.utils.io import load_config
+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.utils.io import load_config
 
 
 class DemoServerTest(unittest.TestCase):

tests/test_encoder.py

@@ -3,9 +3,9 @@ import unittest
 import torch as T
 
 from tests import get_tests_path, get_tests_input_path
-from TTS.speaker_encoder.model import SpeakerEncoder
-from TTS.speaker_encoder.loss import GE2ELoss
-from TTS.utils.io import load_config
+from mozilla_voice_tts.speaker_encoder.model import SpeakerEncoder
+from mozilla_voice_tts.speaker_encoder.loss import GE2ELoss
+from mozilla_voice_tts.utils.io import load_config
 
 
 file_path = get_tests_input_path()

tests/test_layers.py

@@ -1,9 +1,9 @@
 import unittest
 import torch as T
 
-from TTS.tts.layers.tacotron import Prenet, CBHG, Decoder, Encoder
-from TTS.tts.layers.losses import L1LossMasked
-from TTS.tts.utils.generic_utils import sequence_mask
+from mozilla_voice_tts.tts.layers.tacotron import Prenet, CBHG, Decoder, Encoder
+from mozilla_voice_tts.tts.layers.losses import L1LossMasked
+from mozilla_voice_tts.tts.utils.generic_utils import sequence_mask
 
 # pylint: disable=unused-variable
 

tests/test_loader.py

@@ -6,10 +6,10 @@ import numpy as np
 
 from tests import get_tests_path, get_tests_input_path, get_tests_output_path
 from torch.utils.data import DataLoader
-from TTS.utils.io import load_config
-from TTS.utils.audio import AudioProcessor
-from TTS.tts.datasets import TTSDataset
-from TTS.tts.datasets.preprocess import ljspeech
+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
 
 #pylint: disable=unused-variable
 

tests/test_preprocessors.py

@@ -2,7 +2,7 @@ import unittest
 import os
 from tests import get_tests_input_path
 
-from TTS.tts.datasets.preprocess import common_voice
+from mozilla_voice_tts.tts.datasets.preprocess import common_voice
 
 
 class TestPreprocessors(unittest.TestCase):

tests/test_server_package.sh

@@ -12,12 +12,12 @@ pip install --quiet --upgrade pip setuptools wheel
 
 rm -f dist/*.whl
 python setup.py --quiet bdist_wheel --checkpoint tests/outputs/checkpoint_10.pth.tar --model_config tests/outputs/dummy_model_config.json
-pip install --quiet dist/TTS*.whl
+pip install --quiet dist/mozilla_voice_tts*.whl
 
 # this is related to https://github.com/librosa/librosa/issues/1160
 pip install numba==0.48
 
-python -m TTS.server.server &
+python -m mozilla_voice_tts.server.server &
 SERVER_PID=$!
 
 echo 'Waiting for server...'

tests/test_tacotron2_model.py

@@ -6,9 +6,9 @@ import torch
 from tests import get_tests_input_path
 from torch import nn, optim
 
-from TTS.tts.layers.losses import MSELossMasked
-from TTS.tts.models.tacotron2 import Tacotron2
-from TTS.utils.io import load_config
+from mozilla_voice_tts.tts.layers.losses import MSELossMasked
+from mozilla_voice_tts.tts.models.tacotron2 import Tacotron2
+from mozilla_voice_tts.utils.io import load_config
 
 #pylint: disable=unused-variable
 

tests/test_tacotron2_tf_model.py

@@ -7,9 +7,9 @@ tf.get_logger().setLevel('INFO')
 
 from tests import get_tests_path, get_tests_input_path, get_tests_output_path
 
-from TTS.utils.io import load_config
-from TTS.tts.tf.models.tacotron2 import Tacotron2
-from TTS.tts.tf.utils.tflite import convert_tacotron2_to_tflite, load_tflite_model
+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
 

tests/test_tacotron_model.py

@@ -6,9 +6,9 @@ import torch
 from tests import get_tests_input_path
 from torch import nn, optim
 
-from TTS.tts.layers.losses import L1LossMasked
-from TTS.tts.models.tacotron import Tacotron
-from TTS.utils.io import load_config
+from mozilla_voice_tts.tts.layers.losses import L1LossMasked
+from mozilla_voice_tts.tts.models.tacotron import Tacotron
+from mozilla_voice_tts.utils.io import load_config
 
 #pylint: disable=unused-variable
 

tests/test_text_processing.py

@@ -4,9 +4,9 @@ import os
 # pylint: disable=unused-import
 import unittest
 from tests import get_tests_input_path
-from TTS.tts.utils.text import *
+from mozilla_voice_tts.tts.utils.text import *
 from tests import get_tests_path
-from TTS.utils.io import load_config
+from mozilla_voice_tts.utils.io import load_config
 
 conf = load_config(os.path.join(get_tests_input_path(), 'test_config.json'))
 

tests/test_tts_train.sh

@@ -3,11 +3,11 @@
 BASEDIR=$(dirname "$0")
 echo "$BASEDIR"
 # run training
-CUDA_VISIBLE_DEVICES="" python TTS/bin/train_tts.py --config_path $BASEDIR/inputs/test_train_config.json
+CUDA_VISIBLE_DEVICES="" python mozilla_voice_tts/bin/train_tts.py --config_path $BASEDIR/inputs/test_train_config.json
 # find the training folder
 LATEST_FOLDER=$(ls $BASEDIR/train_outputs/| sort | tail -1)
 echo $LATEST_FOLDER
 # continue the previous training
-CUDA_VISIBLE_DEVICES=""  python TTS/bin/train_tts.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER
+CUDA_VISIBLE_DEVICES=""  python mozilla_voice_tts/bin/train_tts.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER
 # remove all the outputs
 rm -rf $BASEDIR/train_outputs/

tests/test_vocoder_datasets.py

@@ -4,10 +4,10 @@ import numpy as np
 from tests import get_tests_path, get_tests_input_path, get_tests_output_path
 from torch.utils.data import DataLoader
 
-from TTS.utils.audio import AudioProcessor
-from TTS.utils.io import load_config
-from TTS.vocoder.datasets.gan_dataset import GANDataset
-from TTS.vocoder.datasets.preprocess import load_wav_data
+from mozilla_voice_tts.utils.audio import AudioProcessor
+from mozilla_voice_tts.utils.io import load_config
+from mozilla_voice_tts.vocoder.datasets.gan_dataset import GANDataset
+from mozilla_voice_tts.vocoder.datasets.preprocess import load_wav_data
 
 file_path = os.path.dirname(os.path.realpath(__file__))
 OUTPATH = os.path.join(get_tests_output_path(), "loader_tests/")

tests/test_vocoder_losses.py

@@ -3,9 +3,9 @@ import os
 import torch
 from tests import get_tests_input_path, get_tests_output_path, get_tests_path
 
-from TTS.utils.audio import AudioProcessor
-from TTS.utils.io import load_config
-from TTS.vocoder.layers.losses import MultiScaleSTFTLoss, STFTLoss, TorchSTFT
+from mozilla_voice_tts.utils.audio import AudioProcessor
+from mozilla_voice_tts.utils.io import load_config
+from mozilla_voice_tts.vocoder.layers.losses import MultiScaleSTFTLoss, STFTLoss, TorchSTFT
 
 TESTS_PATH = get_tests_path()
 

tests/test_vocoder_melgan_discriminator.py

@@ -1,8 +1,8 @@
 import numpy as np
 import torch
 
-from TTS.vocoder.models.melgan_discriminator import MelganDiscriminator
-from TTS.vocoder.models.melgan_multiscale_discriminator import MelganMultiscaleDiscriminator
+from mozilla_voice_tts.vocoder.models.melgan_discriminator import MelganDiscriminator
+from mozilla_voice_tts.vocoder.models.melgan_multiscale_discriminator import MelganMultiscaleDiscriminator
 
 
 def test_melgan_discriminator():

tests/test_vocoder_melgan_generator.py

@@ -1,7 +1,7 @@
 import numpy as np
 import torch
 
-from TTS.vocoder.models.melgan_generator import MelganGenerator
+from mozilla_voice_tts.vocoder.models.melgan_generator import MelganGenerator
 
 def test_melgan_generator():
     model = MelganGenerator()

tests/test_vocoder_parallel_wavegan_discriminator.py

@@ -1,7 +1,7 @@
 import numpy as np
 import torch
 
-from TTS.vocoder.models.parallel_wavegan_discriminator import ParallelWaveganDiscriminator, ResidualParallelWaveganDiscriminator
+from mozilla_voice_tts.vocoder.models.parallel_wavegan_discriminator import ParallelWaveganDiscriminator, ResidualParallelWaveganDiscriminator
 
 
 def test_pwgan_disciminator():

tests/test_vocoder_parallel_wavegan_generator.py

@@ -1,7 +1,7 @@
 import numpy as np
 import torch
 
-from TTS.vocoder.models.parallel_wavegan_generator import ParallelWaveganGenerator
+from mozilla_voice_tts.vocoder.models.parallel_wavegan_generator import ParallelWaveganGenerator
 
 
 def test_pwgan_generator():

tests/test_vocoder_pqmf.py

@@ -5,7 +5,7 @@ import soundfile as sf
 from librosa.core import load
 
 from tests import get_tests_path, get_tests_input_path
-from TTS.vocoder.layers.pqmf import PQMF
+from mozilla_voice_tts.vocoder.layers.pqmf import PQMF
 
 
 TESTS_PATH = get_tests_path()

tests/test_vocoder_rwd.py

@@ -1,7 +1,7 @@
 import torch
 import numpy as np
 
-from TTS.vocoder.models.random_window_discriminator import RandomWindowDiscriminator
+from mozilla_voice_tts.vocoder.models.random_window_discriminator import RandomWindowDiscriminator
 
 
 def test_rwd():

tests/test_vocoder_tf_melgan_generator.py

@@ -1,7 +1,7 @@
 import numpy as np
 import tensorflow as tf
 
-from TTS.vocoder.tf.models.melgan_generator import MelganGenerator
+from mozilla_voice_tts.vocoder.tf.models.melgan_generator import MelganGenerator
 
 
 def test_melgan_generator():

tests/test_vocoder_tf_pqmf.py

@@ -5,7 +5,7 @@ import soundfile as sf
 from librosa.core import load
 
 from tests import get_tests_path, get_tests_input_path
-from TTS.vocoder.tf.layers.pqmf import PQMF
+from mozilla_voice_tts.vocoder.tf.layers.pqmf import PQMF
 
 
 TESTS_PATH = get_tests_path()

tests/test_vocoder_train.sh

@@ -5,11 +5,11 @@ echo "$BASEDIR"
 # create run dir
 mkdir $BASEDIR/train_outputs
 # run training
-CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder.py --config_path $BASEDIR/inputs/test_vocoder_multiband_melgan_config.json
+CUDA_VISIBLE_DEVICES="" python mozilla_voice_tts/bin/train_vocoder.py --config_path $BASEDIR/inputs/test_vocoder_multiband_melgan_config.json
 # find the training folder
 LATEST_FOLDER=$(ls $BASEDIR/outputs/train_outputs/| sort | tail -1)
 echo $LATEST_FOLDER
 # continue the previous training
-CUDA_VISIBLE_DEVICES=""  python TTS/bin/train_vocoder.py --continue_path $BASEDIR/outputs/train_outputs/$LATEST_FOLDER
+CUDA_VISIBLE_DEVICES=""  python mozilla_voice_tts/bin/train_vocoder.py --continue_path $BASEDIR/outputs/train_outputs/$LATEST_FOLDER
 # remove all the outputs
 rm -rf $BASEDIR/train_outputs/