diff --git a/mozilla_voice_tts/__init__.py b/TTS/__init__.py similarity index 100% rename from mozilla_voice_tts/__init__.py rename to TTS/__init__.py diff --git a/mozilla_voice_tts/bin/compute_statistics.py b/TTS/bin/compute_statistics.py similarity index 93% rename from mozilla_voice_tts/bin/compute_statistics.py rename to TTS/bin/compute_statistics.py index b7b1a408..1c6ef94d 100755 --- a/mozilla_voice_tts/bin/compute_statistics.py +++ b/TTS/bin/compute_statistics.py @@ -7,9 +7,9 @@ import argparse import numpy as np from tqdm import tqdm -from mozilla_voice_tts.tts.datasets.preprocess import load_meta_data -from mozilla_voice_tts.utils.io import load_config -from mozilla_voice_tts.utils.audio import AudioProcessor +from TTS.tts.datasets.preprocess import load_meta_data +from TTS.utils.io import load_config +from TTS.utils.audio import AudioProcessor def main(): """Run preprocessing process.""" diff --git a/mozilla_voice_tts/bin/convert_melgan_tflite.py b/TTS/bin/convert_melgan_tflite.py similarity index 74% rename from mozilla_voice_tts/bin/convert_melgan_tflite.py rename to TTS/bin/convert_melgan_tflite.py index 1ede8e05..8df582da 100644 --- a/mozilla_voice_tts/bin/convert_melgan_tflite.py +++ b/TTS/bin/convert_melgan_tflite.py @@ -2,10 +2,10 @@ import argparse -from mozilla_voice_tts.utils.io import load_config -from mozilla_voice_tts.vocoder.tf.utils.generic_utils import setup_generator -from mozilla_voice_tts.vocoder.tf.utils.io import load_checkpoint -from mozilla_voice_tts.vocoder.tf.utils.tflite import convert_melgan_to_tflite +from TTS.utils.io import load_config +from TTS.vocoder.tf.utils.generic_utils import setup_generator +from TTS.vocoder.tf.utils.io import load_checkpoint +from TTS.vocoder.tf.utils.tflite import convert_melgan_to_tflite parser = argparse.ArgumentParser() diff --git a/mozilla_voice_tts/bin/convert_melgan_torch_to_tf.py b/TTS/bin/convert_melgan_torch_to_tf.py similarity index 91% rename from mozilla_voice_tts/bin/convert_melgan_torch_to_tf.py rename to TTS/bin/convert_melgan_torch_to_tf.py index 364c9e54..a006b7b2 100644 --- a/mozilla_voice_tts/bin/convert_melgan_torch_to_tf.py +++ b/TTS/bin/convert_melgan_torch_to_tf.py @@ -6,13 +6,13 @@ import tensorflow as tf import torch from fuzzywuzzy import fuzz -from mozilla_voice_tts.utils.io import load_config -from mozilla_voice_tts.vocoder.tf.utils.convert_torch_to_tf_utils import ( +from TTS.utils.io import load_config +from TTS.vocoder.tf.utils.convert_torch_to_tf_utils import ( compare_torch_tf, convert_tf_name, transfer_weights_torch_to_tf) -from mozilla_voice_tts.vocoder.tf.utils.generic_utils import \ +from TTS.vocoder.tf.utils.generic_utils import \ setup_generator as setup_tf_generator -from mozilla_voice_tts.vocoder.tf.utils.io import save_checkpoint -from mozilla_voice_tts.vocoder.utils.generic_utils import setup_generator +from TTS.vocoder.tf.utils.io import save_checkpoint +from TTS.vocoder.utils.generic_utils import setup_generator # prevent GPU use os.environ['CUDA_VISIBLE_DEVICES'] = '' diff --git a/mozilla_voice_tts/bin/convert_tacotron2_tflite.py b/TTS/bin/convert_tacotron2_tflite.py similarity index 74% rename from mozilla_voice_tts/bin/convert_tacotron2_tflite.py rename to TTS/bin/convert_tacotron2_tflite.py index c7c6891b..2fddf4b0 100644 --- a/mozilla_voice_tts/bin/convert_tacotron2_tflite.py +++ b/TTS/bin/convert_tacotron2_tflite.py @@ -2,11 +2,11 @@ import argparse -from mozilla_voice_tts.utils.io import load_config -from mozilla_voice_tts.tts.utils.text.symbols import symbols, phonemes -from mozilla_voice_tts.tts.tf.utils.generic_utils import setup_model -from mozilla_voice_tts.tts.tf.utils.io import load_checkpoint -from mozilla_voice_tts.tts.tf.utils.tflite import convert_tacotron2_to_tflite +from TTS.utils.io import load_config +from TTS.tts.utils.text.symbols import symbols, phonemes +from TTS.tts.tf.utils.generic_utils import setup_model +from TTS.tts.tf.utils.io import load_checkpoint +from TTS.tts.tf.utils.tflite import convert_tacotron2_to_tflite parser = argparse.ArgumentParser() diff --git a/mozilla_voice_tts/bin/convert_tacotron2_torch_to_tf.py b/TTS/bin/convert_tacotron2_torch_to_tf.py similarity index 95% rename from mozilla_voice_tts/bin/convert_tacotron2_torch_to_tf.py rename to TTS/bin/convert_tacotron2_torch_to_tf.py index 1c4db982..2ba1aa16 100644 --- a/mozilla_voice_tts/bin/convert_tacotron2_torch_to_tf.py +++ b/TTS/bin/convert_tacotron2_torch_to_tf.py @@ -11,13 +11,13 @@ import numpy as np import tensorflow as tf import torch from fuzzywuzzy import fuzz -from mozilla_voice_tts.tts.tf.models.tacotron2 import Tacotron2 -from mozilla_voice_tts.tts.tf.utils.convert_torch_to_tf_utils import ( +from TTS.tts.tf.models.tacotron2 import Tacotron2 +from TTS.tts.tf.utils.convert_torch_to_tf_utils import ( compare_torch_tf, convert_tf_name, transfer_weights_torch_to_tf) -from mozilla_voice_tts.tts.tf.utils.generic_utils import save_checkpoint -from mozilla_voice_tts.tts.utils.generic_utils import setup_model -from mozilla_voice_tts.tts.utils.text.symbols import phonemes, symbols -from mozilla_voice_tts.utils.io import load_config +from TTS.tts.tf.utils.generic_utils import save_checkpoint +from TTS.tts.utils.generic_utils import setup_model +from TTS.tts.utils.text.symbols import phonemes, symbols +from TTS.utils.io import load_config sys.path.append('/home/erogol/Projects') os.environ['CUDA_VISIBLE_DEVICES'] = '' diff --git a/mozilla_voice_tts/bin/distribute_tts.py b/TTS/bin/distribute_tts.py similarity index 100% rename from mozilla_voice_tts/bin/distribute_tts.py rename to TTS/bin/distribute_tts.py diff --git a/mozilla_voice_tts/bin/synthesize.py b/TTS/bin/synthesize.py similarity index 94% rename from mozilla_voice_tts/bin/synthesize.py rename to TTS/bin/synthesize.py index 7d68aef3..bb257548 100644 --- a/mozilla_voice_tts/bin/synthesize.py +++ b/TTS/bin/synthesize.py @@ -10,12 +10,12 @@ import time import torch -from mozilla_voice_tts.tts.utils.generic_utils import setup_model -from mozilla_voice_tts.tts.utils.synthesis import synthesis -from mozilla_voice_tts.tts.utils.text.symbols import make_symbols, phonemes, symbols -from mozilla_voice_tts.utils.audio import AudioProcessor -from mozilla_voice_tts.utils.io import load_config -from mozilla_voice_tts.vocoder.utils.generic_utils import setup_generator +from TTS.tts.utils.generic_utils import setup_model +from TTS.tts.utils.synthesis import synthesis +from TTS.tts.utils.text.symbols import make_symbols, phonemes, symbols +from TTS.utils.audio import AudioProcessor +from TTS.utils.io import load_config +from TTS.vocoder.utils.generic_utils import setup_generator def tts(model, vocoder_model, text, CONFIG, use_cuda, ap, use_gl, speaker_fileid, speaker_embedding=None, gst_style=None): diff --git a/mozilla_voice_tts/bin/train_encoder.py b/TTS/bin/train_encoder.py similarity index 90% rename from mozilla_voice_tts/bin/train_encoder.py rename to TTS/bin/train_encoder.py index 6f41a431..6acaeff1 100644 --- a/mozilla_voice_tts/bin/train_encoder.py +++ b/TTS/bin/train_encoder.py @@ -10,21 +10,21 @@ import traceback import torch from torch.utils.data import DataLoader -from mozilla_voice_tts.speaker_encoder.dataset import MyDataset -from mozilla_voice_tts.speaker_encoder.generic_utils import save_best_model -from mozilla_voice_tts.speaker_encoder.losses import GE2ELoss, AngleProtoLoss -from mozilla_voice_tts.speaker_encoder.model import SpeakerEncoder -from mozilla_voice_tts.speaker_encoder.visual import plot_embeddings -from mozilla_voice_tts.tts.datasets.preprocess import load_meta_data -from mozilla_voice_tts.utils.generic_utils import ( +from TTS.speaker_encoder.dataset import MyDataset +from TTS.speaker_encoder.generic_utils import save_best_model +from TTS.speaker_encoder.losses import GE2ELoss, AngleProtoLoss +from TTS.speaker_encoder.model import SpeakerEncoder +from TTS.speaker_encoder.visual import plot_embeddings +from TTS.tts.datasets.preprocess import load_meta_data +from TTS.utils.generic_utils import ( create_experiment_folder, get_git_branch, remove_experiment_folder, set_init_dict) -from mozilla_voice_tts.utils.io import copy_config_file, load_config -from mozilla_voice_tts.utils.audio import AudioProcessor -from mozilla_voice_tts.utils.generic_utils import count_parameters -from mozilla_voice_tts.utils.radam import RAdam -from mozilla_voice_tts.utils.tensorboard_logger import TensorboardLogger -from mozilla_voice_tts.utils.training import NoamLR, check_update +from TTS.utils.io import copy_config_file, load_config +from TTS.utils.audio import AudioProcessor +from TTS.utils.generic_utils import count_parameters +from TTS.utils.radam import RAdam +from TTS.utils.tensorboard_logger import TensorboardLogger +from TTS.utils.training import NoamLR, check_update torch.backends.cudnn.enabled = True torch.backends.cudnn.benchmark = True diff --git a/mozilla_voice_tts/bin/train_tts.py b/TTS/bin/train_tts.py similarity index 93% rename from mozilla_voice_tts/bin/train_tts.py rename to TTS/bin/train_tts.py index 25b80104..f2641f9d 100644 --- a/mozilla_voice_tts/bin/train_tts.py +++ b/TTS/bin/train_tts.py @@ -11,40 +11,31 @@ import traceback import numpy as np import torch from torch.utils.data import DataLoader - -from mozilla_voice_tts.tts.datasets.preprocess import load_meta_data -from mozilla_voice_tts.tts.datasets.TTSDataset import MyDataset -from mozilla_voice_tts.tts.layers.losses import TacotronLoss -from mozilla_voice_tts.tts.utils.distribute import (DistributedSampler, - apply_gradient_allreduce, - init_distributed, - reduce_tensor) -from mozilla_voice_tts.tts.utils.generic_utils import check_config, setup_model -from mozilla_voice_tts.tts.utils.io import save_best_model, save_checkpoint -from mozilla_voice_tts.tts.utils.measures import alignment_diagonal_score -from mozilla_voice_tts.tts.utils.speakers import (get_speakers, - load_speaker_mapping, - save_speaker_mapping) -from mozilla_voice_tts.tts.utils.synthesis import synthesis -from mozilla_voice_tts.tts.utils.text.symbols import (make_symbols, phonemes, - symbols) -from mozilla_voice_tts.tts.utils.visual import plot_alignment, plot_spectrogram -from mozilla_voice_tts.utils.audio import AudioProcessor -from mozilla_voice_tts.utils.console_logger import ConsoleLogger -from mozilla_voice_tts.utils.generic_utils import (KeepAverage, - count_parameters, - create_experiment_folder, - get_git_branch, - remove_experiment_folder, - set_init_dict) -from mozilla_voice_tts.utils.io import copy_config_file, load_config -from mozilla_voice_tts.utils.radam import RAdam -from mozilla_voice_tts.utils.tensorboard_logger import TensorboardLogger -from mozilla_voice_tts.utils.training import (NoamLR, adam_weight_decay, - check_update, - gradual_training_scheduler, - set_weight_decay, - setup_torch_training_env) +from TTS.tts.datasets.preprocess import load_meta_data +from TTS.tts.datasets.TTSDataset import MyDataset +from TTS.tts.layers.losses import TacotronLoss +from TTS.tts.utils.distribute import (DistributedSampler, + apply_gradient_allreduce, + init_distributed, reduce_tensor) +from TTS.tts.utils.generic_utils import check_config, setup_model +from TTS.tts.utils.io import save_best_model, save_checkpoint +from TTS.tts.utils.measures import alignment_diagonal_score +from TTS.tts.utils.speakers import (get_speakers, load_speaker_mapping, + save_speaker_mapping) +from TTS.tts.utils.synthesis import synthesis +from TTS.tts.utils.text.symbols import make_symbols, phonemes, symbols +from TTS.tts.utils.visual import plot_alignment, plot_spectrogram +from TTS.utils.audio import AudioProcessor +from TTS.utils.console_logger import ConsoleLogger +from TTS.utils.generic_utils import (KeepAverage, count_parameters, + create_experiment_folder, get_git_branch, + remove_experiment_folder, set_init_dict) +from TTS.utils.io import copy_config_file, load_config +from TTS.utils.radam import RAdam +from TTS.utils.tensorboard_logger import TensorboardLogger +from TTS.utils.training import (NoamLR, adam_weight_decay, check_update, + gradual_training_scheduler, set_weight_decay, + setup_torch_training_env) use_cuda, num_gpus = setup_torch_training_env(True, False) diff --git a/mozilla_voice_tts/bin/train_vocoder.py b/TTS/bin/train_vocoder.py similarity index 94% rename from mozilla_voice_tts/bin/train_vocoder.py rename to TTS/bin/train_vocoder.py index 5d87f6bc..b51a55a3 100644 --- a/mozilla_voice_tts/bin/train_vocoder.py +++ b/TTS/bin/train_vocoder.py @@ -8,30 +8,23 @@ from inspect import signature import torch from torch.utils.data import DataLoader - -from mozilla_voice_tts.utils.audio import AudioProcessor -from mozilla_voice_tts.utils.console_logger import ConsoleLogger -from mozilla_voice_tts.utils.generic_utils import (KeepAverage, - count_parameters, - create_experiment_folder, - get_git_branch, - remove_experiment_folder, - set_init_dict) -from mozilla_voice_tts.utils.io import copy_config_file, load_config -from mozilla_voice_tts.utils.radam import RAdam -from mozilla_voice_tts.utils.tensorboard_logger import TensorboardLogger -from mozilla_voice_tts.utils.training import setup_torch_training_env -from mozilla_voice_tts.vocoder.datasets.gan_dataset import GANDataset -from mozilla_voice_tts.vocoder.datasets.preprocess import (load_wav_data, - load_wav_feat_data) +from TTS.utils.audio import AudioProcessor +from TTS.utils.console_logger import ConsoleLogger +from TTS.utils.generic_utils import (KeepAverage, count_parameters, + create_experiment_folder, get_git_branch, + remove_experiment_folder, set_init_dict) +from TTS.utils.io import copy_config_file, load_config +from TTS.utils.radam import RAdam +from TTS.utils.tensorboard_logger import TensorboardLogger +from TTS.utils.training import setup_torch_training_env +from TTS.vocoder.datasets.gan_dataset import GANDataset +from TTS.vocoder.datasets.preprocess import load_wav_data, load_wav_feat_data # from distribute import (DistributedSampler, apply_gradient_allreduce, # init_distributed, reduce_tensor) -from mozilla_voice_tts.vocoder.layers.losses import (DiscriminatorLoss, - GeneratorLoss) -from mozilla_voice_tts.vocoder.utils.generic_utils import (plot_results, - setup_discriminator, - setup_generator) -from mozilla_voice_tts.vocoder.utils.io import save_best_model, save_checkpoint +from TTS.vocoder.layers.losses import DiscriminatorLoss, GeneratorLoss +from TTS.vocoder.utils.generic_utils import (plot_results, setup_discriminator, + setup_generator) +from TTS.vocoder.utils.io import save_best_model, save_checkpoint use_cuda, num_gpus = setup_torch_training_env(True, True) diff --git a/mozilla_voice_tts/server/README.md b/TTS/server/README.md similarity index 98% rename from mozilla_voice_tts/server/README.md rename to TTS/server/README.md index 72b27c98..3c65c961 100644 --- a/mozilla_voice_tts/server/README.md +++ b/TTS/server/README.md @@ -15,7 +15,7 @@ If you have the environment set already for TTS, then you can directly call ```s 3. source /tmp/venv/bin/activate 4. pip install -U pip setuptools wheel 5. pip install -U https//example.com/url/to/python/package.whl -6. python -m mozilla_voice_tts.server.server +6. python -m TTS.server.server You can now open http://localhost:5002 in a browser diff --git a/mozilla_voice_tts/server/__init__.py b/TTS/server/__init__.py similarity index 100% rename from mozilla_voice_tts/server/__init__.py rename to TTS/server/__init__.py diff --git a/mozilla_voice_tts/server/conf.json b/TTS/server/conf.json similarity index 100% rename from mozilla_voice_tts/server/conf.json rename to TTS/server/conf.json diff --git a/mozilla_voice_tts/server/server.py b/TTS/server/server.py similarity index 95% rename from mozilla_voice_tts/server/server.py rename to TTS/server/server.py index 96aff7cc..bd23ea9c 100644 --- a/mozilla_voice_tts/server/server.py +++ b/TTS/server/server.py @@ -3,7 +3,7 @@ import argparse import os from flask import Flask, request, render_template, send_file -from mozilla_voice_tts.server.synthesizer import Synthesizer +from TTS.server.synthesizer import Synthesizer def create_argparser(): @@ -18,8 +18,8 @@ def create_argparser(): parser.add_argument('--wavernn_checkpoint', type=str, default=None, help='path to WaveRNN checkpoint file.') parser.add_argument('--wavernn_config', type=str, default=None, help='path to WaveRNN config file.') parser.add_argument('--is_wavernn_batched', type=convert_boolean, default=False, help='true to use batched WaveRNN.') - parser.add_argument('--vocoder_config', type=str, default=None, help='path to mozilla_voice_tts.vocoder config file.') - parser.add_argument('--vocoder_checkpoint', type=str, default=None, help='path to mozilla_voice_tts.vocoder checkpoint file.') + parser.add_argument('--vocoder_config', type=str, default=None, help='path to TTS.vocoder config file.') + parser.add_argument('--vocoder_checkpoint', type=str, default=None, help='path to TTS.vocoder checkpoint file.') parser.add_argument('--port', type=int, default=5002, help='port to listen on.') parser.add_argument('--use_cuda', type=convert_boolean, default=False, help='true to use CUDA.') parser.add_argument('--debug', type=convert_boolean, default=False, help='true to enable Flask debug mode.') diff --git a/mozilla_voice_tts/server/synthesizer.py b/TTS/server/synthesizer.py similarity index 94% rename from mozilla_voice_tts/server/synthesizer.py rename to TTS/server/synthesizer.py index e6854958..9906291a 100644 --- a/mozilla_voice_tts/server/synthesizer.py +++ b/TTS/server/synthesizer.py @@ -6,16 +6,16 @@ import numpy as np import torch import pysbd -from mozilla_voice_tts.utils.audio import AudioProcessor -from mozilla_voice_tts.utils.io import load_config -from mozilla_voice_tts.tts.utils.generic_utils import setup_model -from mozilla_voice_tts.tts.utils.speakers import load_speaker_mapping -from mozilla_voice_tts.vocoder.utils.generic_utils import setup_generator +from TTS.utils.audio import AudioProcessor +from TTS.utils.io import load_config +from TTS.tts.utils.generic_utils import setup_model +from TTS.tts.utils.speakers import load_speaker_mapping +from TTS.vocoder.utils.generic_utils import setup_generator # pylint: disable=unused-wildcard-import # pylint: disable=wildcard-import -from mozilla_voice_tts.tts.utils.synthesis import * +from TTS.tts.utils.synthesis import * -from mozilla_voice_tts.tts.utils.text import make_symbols, phonemes, symbols +from TTS.tts.utils.text import make_symbols, phonemes, symbols class Synthesizer(object): diff --git a/mozilla_voice_tts/server/templates/index.html b/TTS/server/templates/index.html similarity index 100% rename from mozilla_voice_tts/server/templates/index.html rename to TTS/server/templates/index.html diff --git a/mozilla_voice_tts/speaker_encoder/README.md b/TTS/speaker_encoder/README.md similarity index 94% rename from mozilla_voice_tts/speaker_encoder/README.md rename to TTS/speaker_encoder/README.md index 7706c7d7..b6f541f8 100644 --- a/mozilla_voice_tts/speaker_encoder/README.md +++ b/TTS/speaker_encoder/README.md @@ -10,7 +10,7 @@ Below is an example showing embedding results of various speakers. You can gener Download a pretrained model from [Released Models](https://github.com/mozilla/TTS/wiki/Released-Models) page. -To run the code, you need to follow the same flow as in mozilla_voice_tts. +To run the code, you need to follow the same flow as in TTS. - Define 'config.json' for your needs. Note that, audio parameters should match your TTS model. - Example training call ```python speaker_encoder/train.py --config_path speaker_encoder/config.json --data_path ~/Data/Libri-TTS/train-clean-360``` diff --git a/mozilla_voice_tts/speaker_encoder/__init__.py b/TTS/speaker_encoder/__init__.py similarity index 100% rename from mozilla_voice_tts/speaker_encoder/__init__.py rename to TTS/speaker_encoder/__init__.py diff --git a/mozilla_voice_tts/speaker_encoder/compute_embeddings.py b/TTS/speaker_encoder/compute_embeddings.py similarity index 92% rename from mozilla_voice_tts/speaker_encoder/compute_embeddings.py rename to TTS/speaker_encoder/compute_embeddings.py index 027d3381..cf170c3f 100644 --- a/mozilla_voice_tts/speaker_encoder/compute_embeddings.py +++ b/TTS/speaker_encoder/compute_embeddings.py @@ -6,9 +6,9 @@ import numpy as np from tqdm import tqdm import torch -from mozilla_voice_tts.speaker_encoder.model import SpeakerEncoder -from mozilla_voice_tts.tts.utils.audio import AudioProcessor -from mozilla_voice_tts.tts.utils.generic_utils import load_config +from TTS.speaker_encoder.model import SpeakerEncoder +from TTS.tts.utils.audio import AudioProcessor +from TTS.tts.utils.generic_utils import load_config parser = argparse.ArgumentParser( description='Compute embedding vectors for each wav file in a dataset. ') diff --git a/mozilla_voice_tts/speaker_encoder/config.json b/TTS/speaker_encoder/config.json similarity index 100% rename from mozilla_voice_tts/speaker_encoder/config.json rename to TTS/speaker_encoder/config.json diff --git a/mozilla_voice_tts/speaker_encoder/dataset.py b/TTS/speaker_encoder/dataset.py similarity index 98% rename from mozilla_voice_tts/speaker_encoder/dataset.py rename to TTS/speaker_encoder/dataset.py index d3243c13..e67dd716 100644 --- a/mozilla_voice_tts/speaker_encoder/dataset.py +++ b/TTS/speaker_encoder/dataset.py @@ -9,7 +9,7 @@ class MyDataset(Dataset): num_utter_per_speaker=10, skip_speakers=False, verbose=False): """ Args: - ap (mozilla_voice_tts.tts.utils.AudioProcessor): audio processor object. + ap (TTS.tts.utils.AudioProcessor): audio processor object. meta_data (list): list of dataset instances. seq_len (int): voice segment length in seconds. verbose (bool): print diagnostic information. diff --git a/mozilla_voice_tts/speaker_encoder/generic_utils.py b/TTS/speaker_encoder/generic_utils.py similarity index 100% rename from mozilla_voice_tts/speaker_encoder/generic_utils.py rename to TTS/speaker_encoder/generic_utils.py diff --git a/mozilla_voice_tts/speaker_encoder/losses.py b/TTS/speaker_encoder/losses.py similarity index 100% rename from mozilla_voice_tts/speaker_encoder/losses.py rename to TTS/speaker_encoder/losses.py diff --git a/mozilla_voice_tts/speaker_encoder/model.py b/TTS/speaker_encoder/model.py similarity index 100% rename from mozilla_voice_tts/speaker_encoder/model.py rename to TTS/speaker_encoder/model.py diff --git a/mozilla_voice_tts/speaker_encoder/requirements.txt b/TTS/speaker_encoder/requirements.txt similarity index 100% rename from mozilla_voice_tts/speaker_encoder/requirements.txt rename to TTS/speaker_encoder/requirements.txt diff --git a/mozilla_voice_tts/speaker_encoder/umap.png b/TTS/speaker_encoder/umap.png similarity index 100% rename from mozilla_voice_tts/speaker_encoder/umap.png rename to TTS/speaker_encoder/umap.png diff --git a/mozilla_voice_tts/speaker_encoder/visual.py b/TTS/speaker_encoder/visual.py similarity index 100% rename from mozilla_voice_tts/speaker_encoder/visual.py rename to TTS/speaker_encoder/visual.py diff --git a/mozilla_voice_tts/tts/__init__.py b/TTS/tts/__init__.py similarity index 100% rename from mozilla_voice_tts/tts/__init__.py rename to TTS/tts/__init__.py diff --git a/mozilla_voice_tts/tts/configs/config.json b/TTS/tts/configs/config.json similarity index 100% rename from mozilla_voice_tts/tts/configs/config.json rename to TTS/tts/configs/config.json diff --git a/mozilla_voice_tts/tts/datasets/TTSDataset.py b/TTS/tts/datasets/TTSDataset.py similarity index 97% rename from mozilla_voice_tts/tts/datasets/TTSDataset.py rename to TTS/tts/datasets/TTSDataset.py index 1ecca75f..9c50cb6a 100644 --- a/mozilla_voice_tts/tts/datasets/TTSDataset.py +++ b/TTS/tts/datasets/TTSDataset.py @@ -5,8 +5,8 @@ import torch import random from torch.utils.data import Dataset -from mozilla_voice_tts.tts.utils.text import text_to_sequence, phoneme_to_sequence, pad_with_eos_bos -from mozilla_voice_tts.tts.utils.data import prepare_data, prepare_tensor, prepare_stop_target +from TTS.tts.utils.text import text_to_sequence, phoneme_to_sequence, pad_with_eos_bos +from TTS.tts.utils.data import prepare_data, prepare_tensor, prepare_stop_target class MyDataset(Dataset): @@ -31,7 +31,7 @@ class MyDataset(Dataset): outputs_per_step (int): number of time frames predicted per step. text_cleaner (str): text cleaner used for the dataset. compute_linear_spec (bool): compute linear spectrogram if True. - ap (mozilla_voice_tts.tts.utils.AudioProcessor): audio processor object. + ap (TTS.tts.utils.AudioProcessor): audio processor object. meta_data (list): list of dataset instances. batch_group_size (int): (0) range of batch randomization after sorting sequences by length. diff --git a/mozilla_voice_tts/tts/datasets/__init__.py b/TTS/tts/datasets/__init__.py similarity index 100% rename from mozilla_voice_tts/tts/datasets/__init__.py rename to TTS/tts/datasets/__init__.py diff --git a/mozilla_voice_tts/tts/datasets/preprocess.py b/TTS/tts/datasets/preprocess.py similarity index 99% rename from mozilla_voice_tts/tts/datasets/preprocess.py rename to TTS/tts/datasets/preprocess.py index 2389cd4c..4bfad648 100644 --- a/mozilla_voice_tts/tts/datasets/preprocess.py +++ b/TTS/tts/datasets/preprocess.py @@ -2,7 +2,7 @@ import os from glob import glob import re import sys -from mozilla_voice_tts.tts.utils.generic_utils import split_dataset +from TTS.tts.utils.generic_utils import split_dataset def load_meta_data(datasets): diff --git a/mozilla_voice_tts/tts/layers/__init__.py b/TTS/tts/layers/__init__.py similarity index 100% rename from mozilla_voice_tts/tts/layers/__init__.py rename to TTS/tts/layers/__init__.py diff --git a/mozilla_voice_tts/tts/layers/common_layers.py b/TTS/tts/layers/common_layers.py similarity index 100% rename from mozilla_voice_tts/tts/layers/common_layers.py rename to TTS/tts/layers/common_layers.py diff --git a/mozilla_voice_tts/tts/layers/gst_layers.py b/TTS/tts/layers/gst_layers.py similarity index 100% rename from mozilla_voice_tts/tts/layers/gst_layers.py rename to TTS/tts/layers/gst_layers.py diff --git a/mozilla_voice_tts/tts/layers/losses.py b/TTS/tts/layers/losses.py similarity index 99% rename from mozilla_voice_tts/tts/layers/losses.py rename to TTS/tts/layers/losses.py index ac80ddbf..008a9dd6 100644 --- a/mozilla_voice_tts/tts/layers/losses.py +++ b/TTS/tts/layers/losses.py @@ -2,7 +2,7 @@ import numpy as np import torch from torch import nn from torch.nn import functional -from mozilla_voice_tts.tts.utils.generic_utils import sequence_mask +from TTS.tts.utils.generic_utils import sequence_mask class L1LossMasked(nn.Module): diff --git a/mozilla_voice_tts/tts/layers/tacotron.py b/TTS/tts/layers/tacotron.py similarity index 100% rename from mozilla_voice_tts/tts/layers/tacotron.py rename to TTS/tts/layers/tacotron.py diff --git a/mozilla_voice_tts/tts/layers/tacotron2.py b/TTS/tts/layers/tacotron2.py similarity index 100% rename from mozilla_voice_tts/tts/layers/tacotron2.py rename to TTS/tts/layers/tacotron2.py diff --git a/mozilla_voice_tts/tts/models/__init__.py b/TTS/tts/models/__init__.py similarity index 100% rename from mozilla_voice_tts/tts/models/__init__.py rename to TTS/tts/models/__init__.py diff --git a/mozilla_voice_tts/tts/models/tacotron.py b/TTS/tts/models/tacotron.py similarity index 97% rename from mozilla_voice_tts/tts/models/tacotron.py rename to TTS/tts/models/tacotron.py index 1dcf2fc8..b233cd10 100644 --- a/mozilla_voice_tts/tts/models/tacotron.py +++ b/TTS/tts/models/tacotron.py @@ -2,9 +2,9 @@ import torch from torch import nn -from mozilla_voice_tts.tts.layers.gst_layers import GST -from mozilla_voice_tts.tts.layers.tacotron import Decoder, Encoder, PostCBHG -from mozilla_voice_tts.tts.models.tacotron_abstract import TacotronAbstract +from TTS.tts.layers.gst_layers import GST +from TTS.tts.layers.tacotron import Decoder, Encoder, PostCBHG +from TTS.tts.models.tacotron_abstract import TacotronAbstract class Tacotron(TacotronAbstract): diff --git a/mozilla_voice_tts/tts/models/tacotron2.py b/TTS/tts/models/tacotron2.py similarity index 97% rename from mozilla_voice_tts/tts/models/tacotron2.py rename to TTS/tts/models/tacotron2.py index a9ba442c..0f8e97ab 100644 --- a/mozilla_voice_tts/tts/models/tacotron2.py +++ b/TTS/tts/models/tacotron2.py @@ -1,9 +1,9 @@ import torch from torch import nn -from mozilla_voice_tts.tts.layers.gst_layers import GST -from mozilla_voice_tts.tts.layers.tacotron2 import Decoder, Encoder, Postnet -from mozilla_voice_tts.tts.models.tacotron_abstract import TacotronAbstract +from TTS.tts.layers.gst_layers import GST +from TTS.tts.layers.tacotron2 import Decoder, Encoder, Postnet +from TTS.tts.models.tacotron_abstract import TacotronAbstract # TODO: match function arguments with tacotron class Tacotron2(TacotronAbstract): diff --git a/mozilla_voice_tts/tts/models/tacotron_abstract.py b/TTS/tts/models/tacotron_abstract.py similarity index 99% rename from mozilla_voice_tts/tts/models/tacotron_abstract.py rename to TTS/tts/models/tacotron_abstract.py index d98d03b7..af2e0ae2 100644 --- a/mozilla_voice_tts/tts/models/tacotron_abstract.py +++ b/TTS/tts/models/tacotron_abstract.py @@ -4,7 +4,7 @@ from abc import ABC, abstractmethod import torch from torch import nn -from mozilla_voice_tts.tts.utils.generic_utils import sequence_mask +from TTS.tts.utils.generic_utils import sequence_mask class TacotronAbstract(ABC, nn.Module): diff --git a/mozilla_voice_tts/tts/tf/README.md b/TTS/tts/tf/README.md similarity index 100% rename from mozilla_voice_tts/tts/tf/README.md rename to TTS/tts/tf/README.md diff --git a/mozilla_voice_tts/tts/tf/__init__.py b/TTS/tts/tf/__init__.py similarity index 100% rename from mozilla_voice_tts/tts/tf/__init__.py rename to TTS/tts/tf/__init__.py diff --git a/mozilla_voice_tts/tts/tf/layers/common_layers.py b/TTS/tts/tf/layers/common_layers.py similarity index 100% rename from mozilla_voice_tts/tts/tf/layers/common_layers.py rename to TTS/tts/tf/layers/common_layers.py diff --git a/mozilla_voice_tts/tts/tf/layers/tacotron2.py b/TTS/tts/tf/layers/tacotron2.py similarity index 99% rename from mozilla_voice_tts/tts/tf/layers/tacotron2.py rename to TTS/tts/tf/layers/tacotron2.py index 0dd0593e..20d5f9a4 100644 --- a/mozilla_voice_tts/tts/tf/layers/tacotron2.py +++ b/TTS/tts/tf/layers/tacotron2.py @@ -1,7 +1,7 @@ import tensorflow as tf from tensorflow import keras -from mozilla_voice_tts.tts.tf.utils.tf_utils import shape_list -from mozilla_voice_tts.tts.tf.layers.common_layers import Prenet, Attention +from TTS.tts.tf.utils.tf_utils import shape_list +from TTS.tts.tf.layers.common_layers import Prenet, Attention # from tensorflow_addons.seq2seq import AttentionWrapper # NOTE: linter has a problem with the current TF release diff --git a/mozilla_voice_tts/tts/tf/models/tacotron2.py b/TTS/tts/tf/models/tacotron2.py similarity index 97% rename from mozilla_voice_tts/tts/tf/models/tacotron2.py rename to TTS/tts/tf/models/tacotron2.py index 812fc634..9d470b09 100644 --- a/mozilla_voice_tts/tts/tf/models/tacotron2.py +++ b/TTS/tts/tf/models/tacotron2.py @@ -1,8 +1,8 @@ import tensorflow as tf from tensorflow import keras -from mozilla_voice_tts.tts.tf.layers.tacotron2 import Encoder, Decoder, Postnet -from mozilla_voice_tts.tts.tf.utils.tf_utils import shape_list +from TTS.tts.tf.layers.tacotron2 import Encoder, Decoder, Postnet +from TTS.tts.tf.utils.tf_utils import shape_list #pylint: disable=too-many-ancestors, abstract-method diff --git a/mozilla_voice_tts/tts/tf/utils/convert_torch_to_tf_utils.py b/TTS/tts/tf/utils/convert_torch_to_tf_utils.py similarity index 100% rename from mozilla_voice_tts/tts/tf/utils/convert_torch_to_tf_utils.py rename to TTS/tts/tf/utils/convert_torch_to_tf_utils.py diff --git a/mozilla_voice_tts/tts/tf/utils/generic_utils.py b/TTS/tts/tf/utils/generic_utils.py similarity index 97% rename from mozilla_voice_tts/tts/tf/utils/generic_utils.py rename to TTS/tts/tf/utils/generic_utils.py index f8131abd..7eba946b 100644 --- a/mozilla_voice_tts/tts/tf/utils/generic_utils.py +++ b/TTS/tts/tf/utils/generic_utils.py @@ -77,7 +77,7 @@ def count_parameters(model, c): def setup_model(num_chars, num_speakers, c, enable_tflite=False): print(" > Using model: {}".format(c.model)) - MyModel = importlib.import_module('mozilla_voice_tts.tts.tf.models.' + c.model.lower()) + MyModel = importlib.import_module('TTS.tts.tf.models.' + c.model.lower()) MyModel = getattr(MyModel, c.model) if c.model.lower() in "tacotron": raise NotImplementedError(' [!] Tacotron model is not ready.') diff --git a/mozilla_voice_tts/tts/tf/utils/io.py b/TTS/tts/tf/utils/io.py similarity index 100% rename from mozilla_voice_tts/tts/tf/utils/io.py rename to TTS/tts/tf/utils/io.py diff --git a/mozilla_voice_tts/tts/tf/utils/tf_utils.py b/TTS/tts/tf/utils/tf_utils.py similarity index 100% rename from mozilla_voice_tts/tts/tf/utils/tf_utils.py rename to TTS/tts/tf/utils/tf_utils.py diff --git a/mozilla_voice_tts/tts/tf/utils/tflite.py b/TTS/tts/tf/utils/tflite.py similarity index 100% rename from mozilla_voice_tts/tts/tf/utils/tflite.py rename to TTS/tts/tf/utils/tflite.py diff --git a/mozilla_voice_tts/tts/utils/__init__.py b/TTS/tts/utils/__init__.py similarity index 100% rename from mozilla_voice_tts/tts/utils/__init__.py rename to TTS/tts/utils/__init__.py diff --git a/mozilla_voice_tts/tts/utils/data.py b/TTS/tts/utils/data.py similarity index 100% rename from mozilla_voice_tts/tts/utils/data.py rename to TTS/tts/utils/data.py diff --git a/mozilla_voice_tts/tts/utils/distribute.py b/TTS/tts/utils/distribute.py similarity index 100% rename from mozilla_voice_tts/tts/utils/distribute.py rename to TTS/tts/utils/distribute.py diff --git a/mozilla_voice_tts/tts/utils/generic_utils.py b/TTS/tts/utils/generic_utils.py similarity index 98% rename from mozilla_voice_tts/tts/utils/generic_utils.py rename to TTS/tts/utils/generic_utils.py index d7dca0ac..6eaa2358 100644 --- a/mozilla_voice_tts/tts/utils/generic_utils.py +++ b/TTS/tts/utils/generic_utils.py @@ -3,7 +3,7 @@ import importlib import numpy as np from collections import Counter -from mozilla_voice_tts.utils.generic_utils import check_argument +from TTS.utils.generic_utils import check_argument def split_dataset(items): @@ -46,7 +46,7 @@ def sequence_mask(sequence_length, max_len=None): def setup_model(num_chars, num_speakers, c, speaker_embedding_dim=None): print(" > Using model: {}".format(c.model)) - MyModel = importlib.import_module('mozilla_voice_tts.tts.models.' + c.model.lower()) + MyModel = importlib.import_module('TTS.tts.models.' + c.model.lower()) MyModel = getattr(MyModel, c.model) if c.model.lower() in "tacotron": model = MyModel(num_chars=num_chars, @@ -197,7 +197,7 @@ def check_config(c): # dataloading # pylint: disable=import-outside-toplevel - from mozilla_voice_tts.tts.utils.text import cleaners + from TTS.tts.utils.text import cleaners check_argument('text_cleaner', c, restricted=True, val_type=str, enum_list=dir(cleaners)) check_argument('enable_eos_bos_chars', c, restricted=True, val_type=bool) check_argument('num_loader_workers', c, restricted=True, val_type=int, min_val=0) diff --git a/mozilla_voice_tts/tts/utils/io.py b/TTS/tts/utils/io.py similarity index 100% rename from mozilla_voice_tts/tts/utils/io.py rename to TTS/tts/utils/io.py diff --git a/mozilla_voice_tts/tts/utils/measures.py b/TTS/tts/utils/measures.py similarity index 100% rename from mozilla_voice_tts/tts/utils/measures.py rename to TTS/tts/utils/measures.py diff --git a/mozilla_voice_tts/tts/utils/speakers.py b/TTS/tts/utils/speakers.py similarity index 100% rename from mozilla_voice_tts/tts/utils/speakers.py rename to TTS/tts/utils/speakers.py diff --git a/mozilla_voice_tts/tts/utils/synthesis.py b/TTS/tts/utils/synthesis.py similarity index 98% rename from mozilla_voice_tts/tts/utils/synthesis.py rename to TTS/tts/utils/synthesis.py index 0952c936..76ac7909 100644 --- a/mozilla_voice_tts/tts/utils/synthesis.py +++ b/TTS/tts/utils/synthesis.py @@ -183,11 +183,11 @@ def synthesis(model, """Synthesize voice for the given text. Args: - model (mozilla_voice_tts.tts.models): model to synthesize. + model (TTS.tts.models): model to synthesize. text (str): target text CONFIG (dict): config dictionary to be loaded from config.json. use_cuda (bool): enable cuda. - ap (mozilla_voice_tts.tts.utils.audio.AudioProcessor): audio processor to process + ap (TTS.tts.utils.audio.AudioProcessor): audio processor to process model outputs. speaker_id (int): id of speaker style_wav (str): Uses for style embedding of GST. diff --git a/mozilla_voice_tts/tts/utils/text/__init__.py b/TTS/tts/utils/text/__init__.py similarity index 97% rename from mozilla_voice_tts/tts/utils/text/__init__.py rename to TTS/tts/utils/text/__init__.py index 9301d545..33972f25 100644 --- a/mozilla_voice_tts/tts/utils/text/__init__.py +++ b/TTS/tts/utils/text/__init__.py @@ -4,8 +4,8 @@ import re from packaging import version import phonemizer from phonemizer.phonemize import phonemize -from mozilla_voice_tts.tts.utils.text import cleaners -from mozilla_voice_tts.tts.utils.text.symbols import make_symbols, symbols, phonemes, _phoneme_punctuations, _bos, \ +from TTS.tts.utils.text import cleaners +from TTS.tts.utils.text.symbols import make_symbols, symbols, phonemes, _phoneme_punctuations, _bos, \ _eos # pylint: disable=unnecessary-comprehension diff --git a/mozilla_voice_tts/tts/utils/text/cleaners.py b/TTS/tts/utils/text/cleaners.py similarity index 100% rename from mozilla_voice_tts/tts/utils/text/cleaners.py rename to TTS/tts/utils/text/cleaners.py diff --git a/mozilla_voice_tts/tts/utils/text/cmudict.py b/TTS/tts/utils/text/cmudict.py similarity index 100% rename from mozilla_voice_tts/tts/utils/text/cmudict.py rename to TTS/tts/utils/text/cmudict.py diff --git a/mozilla_voice_tts/tts/utils/text/number_norm.py b/TTS/tts/utils/text/number_norm.py similarity index 100% rename from mozilla_voice_tts/tts/utils/text/number_norm.py rename to TTS/tts/utils/text/number_norm.py diff --git a/mozilla_voice_tts/tts/utils/text/symbols.py b/TTS/tts/utils/text/symbols.py similarity index 100% rename from mozilla_voice_tts/tts/utils/text/symbols.py rename to TTS/tts/utils/text/symbols.py diff --git a/mozilla_voice_tts/tts/utils/visual.py b/TTS/tts/utils/visual.py similarity index 97% rename from mozilla_voice_tts/tts/utils/visual.py rename to TTS/tts/utils/visual.py index 17be49c7..500d7707 100644 --- a/mozilla_voice_tts/tts/utils/visual.py +++ b/TTS/tts/utils/visual.py @@ -3,7 +3,7 @@ import librosa import matplotlib matplotlib.use('Agg') import matplotlib.pyplot as plt -from mozilla_voice_tts.tts.utils.text import phoneme_to_sequence, sequence_to_phoneme +from TTS.tts.utils.text import phoneme_to_sequence, sequence_to_phoneme def plot_alignment(alignment, info=None, fig_size=(16, 10), title=None, output_fig=False): diff --git a/mozilla_voice_tts/utils/__init__.py b/TTS/utils/__init__.py similarity index 100% rename from mozilla_voice_tts/utils/__init__.py rename to TTS/utils/__init__.py diff --git a/mozilla_voice_tts/utils/audio.py b/TTS/utils/audio.py similarity index 99% rename from mozilla_voice_tts/utils/audio.py rename to TTS/utils/audio.py index d81ba809..7a13d14b 100644 --- a/mozilla_voice_tts/utils/audio.py +++ b/TTS/utils/audio.py @@ -5,7 +5,7 @@ import scipy.io.wavfile import scipy.signal import pyworld as pw -from mozilla_voice_tts.tts.utils.data import StandardScaler +from TTS.tts.utils.data import StandardScaler #pylint: disable=too-many-public-methods class AudioProcessor(object): diff --git a/mozilla_voice_tts/utils/console_logger.py b/TTS/utils/console_logger.py similarity index 98% rename from mozilla_voice_tts/utils/console_logger.py rename to TTS/utils/console_logger.py index 0311e0ca..3affd6af 100644 --- a/mozilla_voice_tts/utils/console_logger.py +++ b/TTS/utils/console_logger.py @@ -1,5 +1,5 @@ import datetime -from mozilla_voice_tts.utils.io import AttrDict +from TTS.utils.io import AttrDict tcolors = AttrDict({ diff --git a/mozilla_voice_tts/utils/generic_utils.py b/TTS/utils/generic_utils.py similarity index 100% rename from mozilla_voice_tts/utils/generic_utils.py rename to TTS/utils/generic_utils.py diff --git a/mozilla_voice_tts/utils/io.py b/TTS/utils/io.py similarity index 100% rename from mozilla_voice_tts/utils/io.py rename to TTS/utils/io.py diff --git a/mozilla_voice_tts/utils/radam.py b/TTS/utils/radam.py similarity index 100% rename from mozilla_voice_tts/utils/radam.py rename to TTS/utils/radam.py diff --git a/mozilla_voice_tts/utils/tensorboard_logger.py b/TTS/utils/tensorboard_logger.py similarity index 100% rename from mozilla_voice_tts/utils/tensorboard_logger.py rename to TTS/utils/tensorboard_logger.py diff --git a/mozilla_voice_tts/utils/training.py b/TTS/utils/training.py similarity index 100% rename from mozilla_voice_tts/utils/training.py rename to TTS/utils/training.py diff --git a/mozilla_voice_tts/vocoder/README.md b/TTS/vocoder/README.md similarity index 100% rename from mozilla_voice_tts/vocoder/README.md rename to TTS/vocoder/README.md diff --git a/mozilla_voice_tts/vocoder/__init__.py b/TTS/vocoder/__init__.py similarity index 100% rename from mozilla_voice_tts/vocoder/__init__.py rename to TTS/vocoder/__init__.py diff --git a/mozilla_voice_tts/vocoder/configs/multiband-melgan_and_rwd_config.json b/TTS/vocoder/configs/multiband-melgan_and_rwd_config.json similarity index 100% rename from mozilla_voice_tts/vocoder/configs/multiband-melgan_and_rwd_config.json rename to TTS/vocoder/configs/multiband-melgan_and_rwd_config.json diff --git a/mozilla_voice_tts/vocoder/configs/multiband_melgan_config.json b/TTS/vocoder/configs/multiband_melgan_config.json similarity index 100% rename from mozilla_voice_tts/vocoder/configs/multiband_melgan_config.json rename to TTS/vocoder/configs/multiband_melgan_config.json diff --git a/mozilla_voice_tts/vocoder/configs/multiband_melgan_config_mozilla.json b/TTS/vocoder/configs/multiband_melgan_config_mozilla.json similarity index 100% rename from mozilla_voice_tts/vocoder/configs/multiband_melgan_config_mozilla.json rename to TTS/vocoder/configs/multiband_melgan_config_mozilla.json diff --git a/mozilla_voice_tts/vocoder/configs/parallel_wavegan_config.json b/TTS/vocoder/configs/parallel_wavegan_config.json similarity index 100% rename from mozilla_voice_tts/vocoder/configs/parallel_wavegan_config.json rename to TTS/vocoder/configs/parallel_wavegan_config.json diff --git a/mozilla_voice_tts/vocoder/datasets/__init__.py b/TTS/vocoder/datasets/__init__.py similarity index 100% rename from mozilla_voice_tts/vocoder/datasets/__init__.py rename to TTS/vocoder/datasets/__init__.py diff --git a/mozilla_voice_tts/vocoder/datasets/gan_dataset.py b/TTS/vocoder/datasets/gan_dataset.py similarity index 100% rename from mozilla_voice_tts/vocoder/datasets/gan_dataset.py rename to TTS/vocoder/datasets/gan_dataset.py diff --git a/mozilla_voice_tts/vocoder/datasets/preprocess.py b/TTS/vocoder/datasets/preprocess.py similarity index 100% rename from mozilla_voice_tts/vocoder/datasets/preprocess.py rename to TTS/vocoder/datasets/preprocess.py diff --git a/mozilla_voice_tts/vocoder/layers/__init__.py b/TTS/vocoder/layers/__init__.py similarity index 100% rename from mozilla_voice_tts/vocoder/layers/__init__.py rename to TTS/vocoder/layers/__init__.py diff --git a/mozilla_voice_tts/vocoder/layers/losses.py b/TTS/vocoder/layers/losses.py similarity index 100% rename from mozilla_voice_tts/vocoder/layers/losses.py rename to TTS/vocoder/layers/losses.py diff --git a/mozilla_voice_tts/vocoder/layers/melgan.py b/TTS/vocoder/layers/melgan.py similarity index 100% rename from mozilla_voice_tts/vocoder/layers/melgan.py rename to TTS/vocoder/layers/melgan.py diff --git a/mozilla_voice_tts/vocoder/layers/parallel_wavegan.py b/TTS/vocoder/layers/parallel_wavegan.py similarity index 100% rename from mozilla_voice_tts/vocoder/layers/parallel_wavegan.py rename to TTS/vocoder/layers/parallel_wavegan.py diff --git a/mozilla_voice_tts/vocoder/layers/pqmf.py b/TTS/vocoder/layers/pqmf.py similarity index 100% rename from mozilla_voice_tts/vocoder/layers/pqmf.py rename to TTS/vocoder/layers/pqmf.py diff --git a/mozilla_voice_tts/vocoder/layers/qmf.dat b/TTS/vocoder/layers/qmf.dat similarity index 100% rename from mozilla_voice_tts/vocoder/layers/qmf.dat rename to TTS/vocoder/layers/qmf.dat diff --git a/mozilla_voice_tts/vocoder/layers/upsample.py b/TTS/vocoder/layers/upsample.py similarity index 100% rename from mozilla_voice_tts/vocoder/layers/upsample.py rename to TTS/vocoder/layers/upsample.py diff --git a/mozilla_voice_tts/vocoder/models/__init__.py b/TTS/vocoder/models/__init__.py similarity index 100% rename from mozilla_voice_tts/vocoder/models/__init__.py rename to TTS/vocoder/models/__init__.py diff --git a/mozilla_voice_tts/vocoder/models/melgan_discriminator.py b/TTS/vocoder/models/melgan_discriminator.py similarity index 100% rename from mozilla_voice_tts/vocoder/models/melgan_discriminator.py rename to TTS/vocoder/models/melgan_discriminator.py diff --git a/mozilla_voice_tts/vocoder/models/melgan_generator.py b/TTS/vocoder/models/melgan_generator.py similarity index 98% rename from mozilla_voice_tts/vocoder/models/melgan_generator.py rename to TTS/vocoder/models/melgan_generator.py index 4c35b1eb..9ab98cef 100644 --- a/mozilla_voice_tts/vocoder/models/melgan_generator.py +++ b/TTS/vocoder/models/melgan_generator.py @@ -2,7 +2,7 @@ import torch from torch import nn from torch.nn.utils import weight_norm -from mozilla_voice_tts.vocoder.layers.melgan import ResidualStack +from TTS.vocoder.layers.melgan import ResidualStack class MelganGenerator(nn.Module): diff --git a/mozilla_voice_tts/vocoder/models/melgan_multiscale_discriminator.py b/TTS/vocoder/models/melgan_multiscale_discriminator.py similarity index 94% rename from mozilla_voice_tts/vocoder/models/melgan_multiscale_discriminator.py rename to TTS/vocoder/models/melgan_multiscale_discriminator.py index 69adcc27..0f9cca96 100644 --- a/mozilla_voice_tts/vocoder/models/melgan_multiscale_discriminator.py +++ b/TTS/vocoder/models/melgan_multiscale_discriminator.py @@ -1,6 +1,6 @@ from torch import nn -from mozilla_voice_tts.vocoder.models.melgan_discriminator import MelganDiscriminator +from TTS.vocoder.models.melgan_discriminator import MelganDiscriminator class MelganMultiscaleDiscriminator(nn.Module): diff --git a/mozilla_voice_tts/vocoder/models/multiband_melgan_generator.py b/TTS/vocoder/models/multiband_melgan_generator.py similarity index 91% rename from mozilla_voice_tts/vocoder/models/multiband_melgan_generator.py rename to TTS/vocoder/models/multiband_melgan_generator.py index 5571ed54..15e7426e 100644 --- a/mozilla_voice_tts/vocoder/models/multiband_melgan_generator.py +++ b/TTS/vocoder/models/multiband_melgan_generator.py @@ -1,7 +1,7 @@ import torch -from mozilla_voice_tts.vocoder.models.melgan_generator import MelganGenerator -from mozilla_voice_tts.vocoder.layers.pqmf import PQMF +from TTS.vocoder.models.melgan_generator import MelganGenerator +from TTS.vocoder.layers.pqmf import PQMF class MultibandMelganGenerator(MelganGenerator): diff --git a/mozilla_voice_tts/vocoder/models/parallel_wavegan_discriminator.py b/TTS/vocoder/models/parallel_wavegan_discriminator.py similarity index 98% rename from mozilla_voice_tts/vocoder/models/parallel_wavegan_discriminator.py rename to TTS/vocoder/models/parallel_wavegan_discriminator.py index 8d4f071c..37c22695 100644 --- a/mozilla_voice_tts/vocoder/models/parallel_wavegan_discriminator.py +++ b/TTS/vocoder/models/parallel_wavegan_discriminator.py @@ -2,7 +2,7 @@ import math import torch from torch import nn -from mozilla_voice_tts.vocoder.layers.parallel_wavegan import ResidualBlock +from TTS.vocoder.layers.parallel_wavegan import ResidualBlock class ParallelWaveganDiscriminator(nn.Module): diff --git a/mozilla_voice_tts/vocoder/models/parallel_wavegan_generator.py b/TTS/vocoder/models/parallel_wavegan_generator.py similarity index 97% rename from mozilla_voice_tts/vocoder/models/parallel_wavegan_generator.py rename to TTS/vocoder/models/parallel_wavegan_generator.py index 858da282..d703f327 100644 --- a/mozilla_voice_tts/vocoder/models/parallel_wavegan_generator.py +++ b/TTS/vocoder/models/parallel_wavegan_generator.py @@ -2,8 +2,8 @@ import math import numpy as np import torch -from mozilla_voice_tts.vocoder.layers.parallel_wavegan import ResidualBlock -from mozilla_voice_tts.vocoder.layers.upsample import ConvUpsample +from TTS.vocoder.layers.parallel_wavegan import ResidualBlock +from TTS.vocoder.layers.upsample import ConvUpsample class ParallelWaveganGenerator(torch.nn.Module): diff --git a/mozilla_voice_tts/vocoder/models/random_window_discriminator.py b/TTS/vocoder/models/random_window_discriminator.py similarity index 100% rename from mozilla_voice_tts/vocoder/models/random_window_discriminator.py rename to TTS/vocoder/models/random_window_discriminator.py diff --git a/mozilla_voice_tts/vocoder/pqmf_output.wav b/TTS/vocoder/pqmf_output.wav similarity index 100% rename from mozilla_voice_tts/vocoder/pqmf_output.wav rename to TTS/vocoder/pqmf_output.wav diff --git a/mozilla_voice_tts/vocoder/tf/layers/melgan.py b/TTS/vocoder/tf/layers/melgan.py similarity index 100% rename from mozilla_voice_tts/vocoder/tf/layers/melgan.py rename to TTS/vocoder/tf/layers/melgan.py diff --git a/mozilla_voice_tts/vocoder/tf/layers/pqmf.py b/TTS/vocoder/tf/layers/pqmf.py similarity index 100% rename from mozilla_voice_tts/vocoder/tf/layers/pqmf.py rename to TTS/vocoder/tf/layers/pqmf.py diff --git a/mozilla_voice_tts/vocoder/tf/models/melgan_generator.py b/TTS/vocoder/tf/models/melgan_generator.py similarity index 98% rename from mozilla_voice_tts/vocoder/tf/models/melgan_generator.py rename to TTS/vocoder/tf/models/melgan_generator.py index 60e870cc..9a029df4 100644 --- a/mozilla_voice_tts/vocoder/tf/models/melgan_generator.py +++ b/TTS/vocoder/tf/models/melgan_generator.py @@ -5,7 +5,7 @@ os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' # FATAL logging.getLogger('tensorflow').setLevel(logging.FATAL) import tensorflow as tf -from mozilla_voice_tts.vocoder.tf.layers.melgan import ResidualStack, ReflectionPad1d +from TTS.vocoder.tf.layers.melgan import ResidualStack, ReflectionPad1d #pylint: disable=too-many-ancestors diff --git a/mozilla_voice_tts/vocoder/tf/models/multiband_melgan_generator.py b/TTS/vocoder/tf/models/multiband_melgan_generator.py similarity index 94% rename from mozilla_voice_tts/vocoder/tf/models/multiband_melgan_generator.py rename to TTS/vocoder/tf/models/multiband_melgan_generator.py index 1ae355ce..bdd333ed 100644 --- a/mozilla_voice_tts/vocoder/tf/models/multiband_melgan_generator.py +++ b/TTS/vocoder/tf/models/multiband_melgan_generator.py @@ -1,7 +1,7 @@ import tensorflow as tf -from mozilla_voice_tts.vocoder.tf.models.melgan_generator import MelganGenerator -from mozilla_voice_tts.vocoder.tf.layers.pqmf import PQMF +from TTS.vocoder.tf.models.melgan_generator import MelganGenerator +from TTS.vocoder.tf.layers.pqmf import PQMF #pylint: disable=too-many-ancestors #pylint: disable=abstract-method diff --git a/mozilla_voice_tts/vocoder/tf/utils/__init__.py b/TTS/vocoder/tf/utils/__init__.py similarity index 100% rename from mozilla_voice_tts/vocoder/tf/utils/__init__.py rename to TTS/vocoder/tf/utils/__init__.py diff --git a/mozilla_voice_tts/vocoder/tf/utils/convert_torch_to_tf_utils.py b/TTS/vocoder/tf/utils/convert_torch_to_tf_utils.py similarity index 100% rename from mozilla_voice_tts/vocoder/tf/utils/convert_torch_to_tf_utils.py rename to TTS/vocoder/tf/utils/convert_torch_to_tf_utils.py diff --git a/mozilla_voice_tts/vocoder/tf/utils/generic_utils.py b/TTS/vocoder/tf/utils/generic_utils.py similarity index 93% rename from mozilla_voice_tts/vocoder/tf/utils/generic_utils.py rename to TTS/vocoder/tf/utils/generic_utils.py index 6f1622dc..0daf2d6e 100644 --- a/mozilla_voice_tts/vocoder/tf/utils/generic_utils.py +++ b/TTS/vocoder/tf/utils/generic_utils.py @@ -9,7 +9,7 @@ def to_camel(text): def setup_generator(c): print(" > Generator Model: {}".format(c.generator_model)) - MyModel = importlib.import_module('mozilla_voice_tts.vocoder.tf.models.' + + MyModel = importlib.import_module('TTS.vocoder.tf.models.' + c.generator_model.lower()) MyModel = getattr(MyModel, to_camel(c.generator_model)) if c.generator_model in 'melgan_generator': diff --git a/mozilla_voice_tts/vocoder/tf/utils/io.py b/TTS/vocoder/tf/utils/io.py similarity index 100% rename from mozilla_voice_tts/vocoder/tf/utils/io.py rename to TTS/vocoder/tf/utils/io.py diff --git a/mozilla_voice_tts/vocoder/tf/utils/tflite.py b/TTS/vocoder/tf/utils/tflite.py similarity index 100% rename from mozilla_voice_tts/vocoder/tf/utils/tflite.py rename to TTS/vocoder/tf/utils/tflite.py diff --git a/mozilla_voice_tts/vocoder/utils/__init__.py b/TTS/vocoder/utils/__init__.py similarity index 100% rename from mozilla_voice_tts/vocoder/utils/__init__.py rename to TTS/vocoder/utils/__init__.py diff --git a/mozilla_voice_tts/vocoder/utils/generic_utils.py b/TTS/vocoder/utils/generic_utils.py similarity index 94% rename from mozilla_voice_tts/vocoder/utils/generic_utils.py rename to TTS/vocoder/utils/generic_utils.py index e28dd771..4b9a7c3f 100644 --- a/mozilla_voice_tts/vocoder/utils/generic_utils.py +++ b/TTS/vocoder/utils/generic_utils.py @@ -3,7 +3,7 @@ import importlib import numpy as np from matplotlib import pyplot as plt -from mozilla_voice_tts.tts.utils.visual import plot_spectrogram +from TTS.tts.utils.visual import plot_spectrogram def plot_results(y_hat, y, ap, global_step, name_prefix): @@ -44,7 +44,7 @@ def to_camel(text): def setup_generator(c): print(" > Generator Model: {}".format(c.generator_model)) - MyModel = importlib.import_module('mozilla_voice_tts.vocoder.models.' + + MyModel = importlib.import_module('TTS.vocoder.models.' + c.generator_model.lower()) MyModel = getattr(MyModel, to_camel(c.generator_model)) if c.generator_model in 'melgan_generator': @@ -89,9 +89,9 @@ def setup_discriminator(c): print(" > Discriminator Model: {}".format(c.discriminator_model)) if 'parallel_wavegan' in c.discriminator_model: MyModel = importlib.import_module( - 'mozilla_voice_tts.vocoder.models.parallel_wavegan_discriminator') + 'TTS.vocoder.models.parallel_wavegan_discriminator') else: - MyModel = importlib.import_module('mozilla_voice_tts.vocoder.models.' + + MyModel = importlib.import_module('TTS.vocoder.models.' + c.discriminator_model.lower()) MyModel = getattr(MyModel, to_camel(c.discriminator_model.lower())) if c.discriminator_model in 'random_window_discriminator': diff --git a/mozilla_voice_tts/vocoder/utils/io.py b/TTS/vocoder/utils/io.py similarity index 100% rename from mozilla_voice_tts/vocoder/utils/io.py rename to TTS/vocoder/utils/io.py diff --git a/notebooks/DDC_TTS_and_MultiBand_MelGAN_Example.ipynb b/notebooks/DDC_TTS_and_MultiBand_MelGAN_Example.ipynb index 782e4f61..dc582830 100644 --- a/notebooks/DDC_TTS_and_MultiBand_MelGAN_Example.ipynb +++ b/notebooks/DDC_TTS_and_MultiBand_MelGAN_Example.ipynb @@ -154,11 +154,11 @@ "import time\n", "import IPython\n", "\n", - "from mozilla_voice_tts.tts.utils.generic_utils import setup_model\n", - "from mozilla_voice_tts.utils.io import load_config\n", - "from mozilla_voice_tts.tts.utils.text.symbols import symbols, phonemes\n", - "from mozilla_voice_tts.utils.audio import AudioProcessor\n", - "from mozilla_voice_tts.tts.utils.synthesis import synthesis" + "from TTS.tts.utils.generic_utils import setup_model\n", + "from TTS.utils.io import load_config\n", + "from TTS.tts.utils.text.symbols import symbols, phonemes\n", + "from TTS.utils.audio import AudioProcessor\n", + "from TTS.tts.utils.synthesis import synthesis" ], "execution_count": null, "outputs": [] @@ -280,7 +280,7 @@ "tags": [] }, "source": [ - "from mozilla_voice_tts.vocoder.utils.generic_utils import setup_generator\n", + "from TTS.vocoder.utils.generic_utils import setup_generator\n", "\n", "# LOAD VOCODER MODEL\n", "vocoder_model = setup_generator(VOCODER_CONFIG)\n", diff --git a/notebooks/DDC_TTS_and_MultiBand_MelGAN_TFLite_Example.ipynb b/notebooks/DDC_TTS_and_MultiBand_MelGAN_TFLite_Example.ipynb index 753d5157..57d9261b 100644 --- a/notebooks/DDC_TTS_and_MultiBand_MelGAN_TFLite_Example.ipynb +++ b/notebooks/DDC_TTS_and_MultiBand_MelGAN_TFLite_Example.ipynb @@ -1140,12 +1140,12 @@ "import time\n", "import IPython\n", "\n", - "from mozilla_voice_tts.tf.utils.tflite import load_tflite_model\n", - "from mozilla_voice_tts.tf.utils.io import load_checkpoint\n", - "from mozilla_voice_tts.utils.io import load_config\n", - "from mozilla_voice_tts.utils.text.symbols import symbols, phonemes\n", - "from mozilla_voice_tts.utils.audio import AudioProcessor\n", - "from mozilla_voice_tts.tts.utils.synthesis import synthesis" + "from TTS.tf.utils.tflite import load_tflite_model\n", + "from TTS.tf.utils.io import load_checkpoint\n", + "from TTS.utils.io import load_config\n", + "from TTS.utils.text.symbols import symbols, phonemes\n", + "from TTS.utils.audio import AudioProcessor\n", + "from TTS.tts.utils.synthesis import synthesis" ], "execution_count": null, "outputs": [] diff --git a/notebooks/DDC_TTS_and_MultiBand_MelGAN_TF_Example.ipynb b/notebooks/DDC_TTS_and_MultiBand_MelGAN_TF_Example.ipynb index e675948c..5264b125 100644 --- a/notebooks/DDC_TTS_and_MultiBand_MelGAN_TF_Example.ipynb +++ b/notebooks/DDC_TTS_and_MultiBand_MelGAN_TF_Example.ipynb @@ -31,7 +31,7 @@ "colab_type": "text" }, "source": [ - "**These models are converted from released [PyTorch models](https://colab.research.google.com/drive/1u_16ZzHjKYFn1HNVuA4Qf_i2MMFB9olY?usp=sharing) using our TF utilities provided in Mozilla mozilla_voice_tts.**\n", + "**These models are converted from released [PyTorch models](https://colab.research.google.com/drive/1u_16ZzHjKYFn1HNVuA4Qf_i2MMFB9olY?usp=sharing) using our TF utilities provided in Mozilla TTS.**\n", "\n", "These TF models support TF 2.2 and for different versions you might need to\n", "regenerate them. \n", @@ -154,12 +154,12 @@ "import time\n", "import IPython\n", "\n", - "from mozilla_voice_tts.tts.tf.utils.generic_utils import setup_model\n", - "from mozilla_voice_tts.tts.tf.utils.io import load_checkpoint\n", - "from mozilla_voice_tts.utils.io import load_config\n", - "from mozilla_voice_tts.tts.utils.text.symbols import symbols, phonemes\n", - "from mozilla_voice_tts.utils.audio import AudioProcessor\n", - "from mozilla_voice_tts.tts.utils.synthesis import synthesis" + "from TTS.tts.tf.utils.generic_utils import setup_model\n", + "from TTS.tts.tf.utils.io import load_checkpoint\n", + "from TTS.utils.io import load_config\n", + "from TTS.tts.utils.text.symbols import symbols, phonemes\n", + "from TTS.utils.audio import AudioProcessor\n", + "from TTS.tts.utils.synthesis import synthesis" ], "execution_count": null, "outputs": [] @@ -270,8 +270,8 @@ "outputId": "2cc3deae-144f-4465-da3b-98628d948506" }, "source": [ - "from mozilla_voice_tts.vocoder.tf.utils.generic_utils import setup_generator\n", - "from mozilla_voice_tts.vocoder.tf.utils.io import load_checkpoint\n", + "from TTS.vocoder.tf.utils.generic_utils import setup_generator\n", + "from TTS.vocoder.tf.utils.io import load_checkpoint\n", "\n", "# LOAD VOCODER MODEL\n", "vocoder_model = setup_generator(VOCODER_CONFIG)\n", diff --git a/notebooks/DDC_TTS_and_ParallelWaveGAN_Example.ipynb b/notebooks/DDC_TTS_and_ParallelWaveGAN_Example.ipynb index 661ef579..00de8bbd 100644 --- a/notebooks/DDC_TTS_and_ParallelWaveGAN_Example.ipynb +++ b/notebooks/DDC_TTS_and_ParallelWaveGAN_Example.ipynb @@ -154,11 +154,11 @@ "import time\n", "import IPython\n", "\n", - "from mozilla_voice_tts.tts.utils.generic_utils import setup_model\n", - "from mozilla_voice_tts.utils.io import load_config\n", - "from mozilla_voice_tts.tts.utils.text.symbols import symbols, phonemes\n", - "from mozilla_voice_tts.utils.audio import AudioProcessor\n", - "from mozilla_voice_tts.tts.utils.synthesis import synthesis" + "from TTS.tts.utils.generic_utils import setup_model\n", + "from TTS.utils.io import load_config\n", + "from TTS.tts.utils.text.symbols import symbols, phonemes\n", + "from TTS.utils.audio import AudioProcessor\n", + "from TTS.tts.utils.synthesis import synthesis" ], "execution_count": null, "outputs": [] @@ -280,7 +280,7 @@ "tags": [] }, "source": [ - "from mozilla_voice_tts.vocoder.utils.generic_utils import setup_generator\n", + "from TTS.vocoder.utils.generic_utils import setup_generator\n", "\n", "# LOAD VOCODER MODEL\n", "vocoder_model = setup_generator(VOCODER_CONFIG)\n", diff --git a/notebooks/ExtractTTSpectrogram.ipynb b/notebooks/ExtractTTSpectrogram.ipynb index 37687517..b28489e0 100644 --- a/notebooks/ExtractTTSpectrogram.ipynb +++ b/notebooks/ExtractTTSpectrogram.ipynb @@ -22,12 +22,12 @@ "import numpy as np\n", "from tqdm import tqdm as tqdm\n", "from torch.utils.data import DataLoader\n", - "from mozilla_voice_tts.tts.datasets.TTSDataset import MyDataset\n", - "from mozilla_voice_tts.tts.layers.losses import L1LossMasked\n", - "from mozilla_voice_tts.tts.utils.audio import AudioProcessor\n", - "from mozilla_voice_tts.tts.utils.visual import plot_spectrogram\n", - "from mozilla_voice_tts.tts.utils.generic_utils import load_config, setup_model, sequence_mask\n", - "from mozilla_voice_tts.tts.utils.text.symbols import make_symbols, symbols, phonemes\n", + "from TTS.tts.datasets.TTSDataset import MyDataset\n", + "from TTS.tts.layers.losses import L1LossMasked\n", + "from TTS.tts.utils.audio import AudioProcessor\n", + "from TTS.tts.utils.visual import plot_spectrogram\n", + "from TTS.tts.utils.generic_utils import load_config, setup_model, sequence_mask\n", + "from TTS.tts.utils.text.symbols import make_symbols, symbols, phonemes\n", "\n", "%matplotlib inline\n", "\n", @@ -108,7 +108,7 @@ "metadata": {}, "outputs": [], "source": [ - "preprocessor = importlib.import_module('mozilla_voice_tts.tts.datasets.preprocess')\n", + "preprocessor = importlib.import_module('TTS.tts.datasets.preprocess')\n", "preprocessor = getattr(preprocessor, DATASET.lower())\n", "meta_data = preprocessor(DATA_PATH,METADATA_FILE)\n", "dataset = MyDataset(checkpoint['r'], C.text_cleaner, False, ap, meta_data,tp=C.characters if 'characters' in C.keys() else None, use_phonemes=C.use_phonemes, phoneme_cache_path=C.phoneme_cache_path, enable_eos_bos=C.enable_eos_bos_chars)\n", diff --git a/notebooks/TestAttention.ipynb b/notebooks/TestAttention.ipynb index 08d3acf8..51413099 100644 --- a/notebooks/TestAttention.ipynb +++ b/notebooks/TestAttention.ipynb @@ -36,14 +36,14 @@ "import librosa\n", "import librosa.display\n", "\n", - "from mozilla_voice_tts.tts.layers import *\n", - "from mozilla_voice_tts.tts.utils.audio import AudioProcessor\n", - "from mozilla_voice_tts.tts.utils.generic_utils import setup_model\n", - "from mozilla_voice_tts.tts.utils.io import load_config\n", - "from mozilla_voice_tts.tts.utils.text import text_to_sequence\n", - "from mozilla_voice_tts.tts.utils.synthesis import synthesis\n", - "from mozilla_voice_tts.tts.utils.visual import plot_alignment\n", - "from mozilla_voice_tts.tts.utils.measures import alignment_diagonal_score\n", + "from TTS.tts.layers import *\n", + "from TTS.tts.utils.audio import AudioProcessor\n", + "from TTS.tts.utils.generic_utils import setup_model\n", + "from TTS.tts.utils.io import load_config\n", + "from TTS.tts.utils.text import text_to_sequence\n", + "from TTS.tts.utils.synthesis import synthesis\n", + "from TTS.tts.utils.visual import plot_alignment\n", + "from TTS.tts.utils.measures import alignment_diagonal_score\n", "\n", "import IPython\n", "from IPython.display import Audio\n", @@ -96,7 +96,7 @@ "outputs": [], "source": [ "# LOAD TTS MODEL\n", - "from mozilla_voice_tts.tts.utils.text.symbols import make_symbols, symbols, phonemes\n", + "from TTS.tts.utils.text.symbols import make_symbols, symbols, phonemes\n", "\n", "# multi speaker \n", "if CONFIG.use_speaker_embedding:\n", diff --git a/notebooks/Tutorial_Converting_PyTorch_to_TF_to_TFlite.ipynb b/notebooks/Tutorial_Converting_PyTorch_to_TF_to_TFlite.ipynb index 625c0c0a..0a9090e8 100644 --- a/notebooks/Tutorial_Converting_PyTorch_to_TF_to_TFlite.ipynb +++ b/notebooks/Tutorial_Converting_PyTorch_to_TF_to_TFlite.ipynb @@ -276,12 +276,12 @@ "import time\n", "import IPython\n", "\n", - "from mozilla_voice_tts.tts.tf.utils.tflite import load_tflite_model\n", - "from mozilla_voice_tts.tts.tf.utils.io import load_checkpoint\n", - "from mozilla_voice_tts.utils.io import load_config\n", - "from mozilla_voice_tts.tts.utils.text.symbols import symbols, phonemes\n", - "from mozilla_voice_tts.utils.audio import AudioProcessor\n", - "from mozilla_voice_tts.tts.utils.synthesis import synthesis" + "from TTS.tts.tf.utils.tflite import load_tflite_model\n", + "from TTS.tts.tf.utils.io import load_checkpoint\n", + "from TTS.utils.io import load_config\n", + "from TTS.tts.utils.text.symbols import symbols, phonemes\n", + "from TTS.utils.audio import AudioProcessor\n", + "from TTS.tts.utils.synthesis import synthesis" ], "execution_count": null, "outputs": [] diff --git a/notebooks/dataset_analysis/AnalyzeDataset-Copy1.ipynb b/notebooks/dataset_analysis/AnalyzeDataset-Copy1.ipynb index 0fe81d4e..390b20e2 100644 --- a/notebooks/dataset_analysis/AnalyzeDataset-Copy1.ipynb +++ b/notebooks/dataset_analysis/AnalyzeDataset-Copy1.ipynb @@ -31,7 +31,7 @@ "from multiprocessing import Pool\n", "from matplotlib import pylab as plt\n", "from collections import Counter\n", - "from mozilla_voice_tts.tts.datasets.preprocess import *\n", + "from TTS.tts.datasets.preprocess import *\n", "%matplotlib inline" ] }, diff --git a/notebooks/dataset_analysis/AnalyzeDataset.ipynb b/notebooks/dataset_analysis/AnalyzeDataset.ipynb index e7848fab..62870fdc 100644 --- a/notebooks/dataset_analysis/AnalyzeDataset.ipynb +++ b/notebooks/dataset_analysis/AnalyzeDataset.ipynb @@ -27,7 +27,7 @@ "from multiprocessing import Pool\n", "from matplotlib import pylab as plt\n", "from collections import Counter\n", - "from mozilla_voice_tts.tts.datasets.preprocess import *\n", + "from TTS.tts.datasets.preprocess import *\n", "%matplotlib inline" ] }, diff --git a/setup.py b/setup.py index c40f77e6..4aa3d52a 100644 --- a/setup.py +++ b/setup.py @@ -23,8 +23,8 @@ version = '0.0.4' # Adapted from https://github.com/pytorch/pytorch cwd = os.path.dirname(os.path.abspath(__file__)) -if os.getenv('MOZILLA_VOICE_TTS_PYTORCH_BUILD_VERSION'): - version = os.getenv('MOZILLA_VOICE_TTS_PYTORCH_BUILD_VERSION') +if os.getenv('TTS_PYTORCH_BUILD_VERSION'): + version = os.getenv('TTS_PYTORCH_BUILD_VERSION') else: try: sha = subprocess.check_output( @@ -56,11 +56,11 @@ class develop(setuptools.command.develop.develop): # The documentation for this feature is in server/README.md -package_data = ['mozilla_voice_tts/server/templates/*'] +package_data = ['TTS/server/templates/*'] if 'bdist_wheel' in unknown_args and args.checkpoint and args.model_config: print('Embedding model in wheel file...') - model_dir = os.path.join('mozilla_voice_tts', 'server', 'model') + model_dir = os.path.join('TTS', 'server', 'model') tts_dir = os.path.join(model_dir, 'tts') os.makedirs(tts_dir, exist_ok=True) embedded_checkpoint_path = os.path.join(tts_dir, 'checkpoint.pth.tar') @@ -87,7 +87,7 @@ requirements = { setup( - name='mozilla_voice_tts', + name='TTS', version=version, url='https://github.com/mozilla/TTS', author='Eren Gölge', @@ -96,7 +96,7 @@ setup( license='MPL-2.0', entry_points={ 'console_scripts': [ - 'tts-server = mozilla_voice_tts.server.server:main' + 'tts-server = TTS.server.server:main' ] }, packages=find_packages(include=['TTS*']), diff --git a/tests/symbols_tests.py b/tests/symbols_tests.py index e3cb23da..4e70b9d5 100644 --- a/tests/symbols_tests.py +++ b/tests/symbols_tests.py @@ -1,8 +1,7 @@ import unittest -from mozilla_voice_tts.tts.utils.text import phonemes +from TTS.tts.utils.text import phonemes class SymbolsTest(unittest.TestCase): def test_uniqueness(self): #pylint: disable=no-self-use assert sorted(phonemes) == sorted(list(set(phonemes))), " {} vs {} ".format(len(phonemes), len(set(phonemes))) - \ No newline at end of file diff --git a/tests/test_audio.py b/tests/test_audio.py index 6796c644..dcc511e2 100644 --- a/tests/test_audio.py +++ b/tests/test_audio.py @@ -3,8 +3,8 @@ import unittest 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 +from TTS.utils.audio import AudioProcessor +from TTS.utils.io import load_config TESTS_PATH = get_tests_path() OUT_PATH = os.path.join(get_tests_output_path(), "audio_tests") diff --git a/tests/test_demo_server.py b/tests/test_demo_server.py index 2ec15aba..0576430c 100644 --- a/tests/test_demo_server.py +++ b/tests/test_demo_server.py @@ -2,13 +2,11 @@ import os import unittest from tests import get_tests_input_path, get_tests_output_path - -from mozilla_voice_tts.server.synthesizer import Synthesizer -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 +from TTS.server.synthesizer import Synthesizer +from TTS.tts.utils.generic_utils import setup_model +from TTS.tts.utils.io import save_checkpoint +from TTS.tts.utils.text.symbols import make_symbols, phonemes, symbols +from TTS.utils.io import load_config class DemoServerTest(unittest.TestCase): diff --git a/tests/test_encoder.py b/tests/test_encoder.py index 46266f29..a646eaa6 100644 --- a/tests/test_encoder.py +++ b/tests/test_encoder.py @@ -4,9 +4,9 @@ import unittest import torch as T from tests import get_tests_input_path -from mozilla_voice_tts.speaker_encoder.losses import GE2ELoss, AngleProtoLoss -from mozilla_voice_tts.speaker_encoder.model import SpeakerEncoder -from mozilla_voice_tts.utils.io import load_config +from TTS.speaker_encoder.losses import GE2ELoss, AngleProtoLoss +from TTS.speaker_encoder.model import SpeakerEncoder +from TTS.utils.io import load_config file_path = get_tests_input_path() c = load_config(os.path.join(file_path, "test_config.json")) diff --git a/tests/test_layers.py b/tests/test_layers.py index 0b5315c5..57be51e5 100644 --- a/tests/test_layers.py +++ b/tests/test_layers.py @@ -1,9 +1,9 @@ import unittest import torch as T -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 +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 # pylint: disable=unused-variable diff --git a/tests/test_loader.py b/tests/test_loader.py index 9f084f8f..b79aad19 100644 --- a/tests/test_loader.py +++ b/tests/test_loader.py @@ -7,10 +7,10 @@ import torch from tests import get_tests_input_path, get_tests_output_path from torch.utils.data import DataLoader -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 +from TTS.tts.datasets import TTSDataset +from TTS.tts.datasets.preprocess import ljspeech +from TTS.utils.audio import AudioProcessor +from TTS.utils.io import load_config #pylint: disable=unused-variable diff --git a/tests/test_preprocessors.py b/tests/test_preprocessors.py index 5c875ce6..1c7ad46f 100644 --- a/tests/test_preprocessors.py +++ b/tests/test_preprocessors.py @@ -2,7 +2,7 @@ import unittest import os from tests import get_tests_input_path -from mozilla_voice_tts.tts.datasets.preprocess import common_voice +from TTS.tts.datasets.preprocess import common_voice class TestPreprocessors(unittest.TestCase): diff --git a/tests/test_server_package.sh b/tests/test_server_package.sh index a5205cdd..83ffc6f0 100755 --- a/tests/test_server_package.sh +++ b/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/mozilla_voice_tts*.whl +pip install --quiet dist/TTS*.whl # this is related to https://github.com/librosa/librosa/issues/1160 pip install numba==0.48 -python -m mozilla_voice_tts.server.server & +python -m TTS.server.server & SERVER_PID=$! echo 'Waiting for server...' diff --git a/tests/test_tacotron2_model.py b/tests/test_tacotron2_model.py index 28d39de5..7fee7d18 100644 --- a/tests/test_tacotron2_model.py +++ b/tests/test_tacotron2_model.py @@ -6,10 +6,10 @@ import torch from tests import get_tests_input_path from torch import nn, optim -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 -from mozilla_voice_tts.utils.audio import AudioProcessor +from TTS.tts.layers.losses import MSELossMasked +from TTS.tts.models.tacotron2 import Tacotron2 +from TTS.utils.io import load_config +from TTS.utils.audio import AudioProcessor #pylint: disable=unused-variable diff --git a/tests/test_tacotron2_tf_model.py b/tests/test_tacotron2_tf_model.py index 50853e9a..b792cfa7 100644 --- a/tests/test_tacotron2_tf_model.py +++ b/tests/test_tacotron2_tf_model.py @@ -5,11 +5,10 @@ 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 +from TTS.tts.tf.models.tacotron2 import Tacotron2 +from TTS.tts.tf.utils.tflite import (convert_tacotron2_to_tflite, + load_tflite_model) +from TTS.utils.io import load_config tf.get_logger().setLevel('INFO') diff --git a/tests/test_tacotron_model.py b/tests/test_tacotron_model.py index 0b80243f..124f0b5e 100644 --- a/tests/test_tacotron_model.py +++ b/tests/test_tacotron_model.py @@ -6,10 +6,10 @@ import torch from tests import get_tests_input_path from torch import nn, optim -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 -from mozilla_voice_tts.utils.audio import AudioProcessor +from TTS.tts.layers.losses import L1LossMasked +from TTS.tts.models.tacotron import Tacotron +from TTS.utils.io import load_config +from TTS.utils.audio import AudioProcessor #pylint: disable=unused-variable diff --git a/tests/test_text_processing.py b/tests/test_text_processing.py index 61c2a407..1eb9f9a8 100644 --- a/tests/test_text_processing.py +++ b/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 mozilla_voice_tts.tts.utils.text import * +from TTS.tts.utils.text import * from tests import get_tests_path -from mozilla_voice_tts.utils.io import load_config +from TTS.utils.io import load_config conf = load_config(os.path.join(get_tests_input_path(), 'test_config.json')) diff --git a/tests/test_tts_train.sh b/tests/test_tts_train.sh index b7adbdd0..55379a1e 100755 --- a/tests/test_tts_train.sh +++ b/tests/test_tts_train.sh @@ -3,11 +3,11 @@ BASEDIR=$(dirname "$0") echo "$BASEDIR" # run training -CUDA_VISIBLE_DEVICES="" python mozilla_voice_tts/bin/train_tts.py --config_path $BASEDIR/inputs/test_train_config.json +CUDA_VISIBLE_DEVICES="" python 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 mozilla_voice_tts/bin/train_tts.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER +CUDA_VISIBLE_DEVICES="" python TTS/bin/train_tts.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER # remove all the outputs rm -rf $BASEDIR/train_outputs/ diff --git a/tests/test_vocoder_datasets.py b/tests/test_vocoder_datasets.py index bdfebfc5..2a487d9a 100644 --- a/tests/test_vocoder_datasets.py +++ b/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 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 +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 file_path = os.path.dirname(os.path.realpath(__file__)) OUTPATH = os.path.join(get_tests_output_path(), "loader_tests/") diff --git a/tests/test_vocoder_losses.py b/tests/test_vocoder_losses.py index 6cf0f6a9..965e68ad 100644 --- a/tests/test_vocoder_losses.py +++ b/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 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 +from TTS.utils.audio import AudioProcessor +from TTS.utils.io import load_config +from TTS.vocoder.layers.losses import MultiScaleSTFTLoss, STFTLoss, TorchSTFT TESTS_PATH = get_tests_path() diff --git a/tests/test_vocoder_melgan_discriminator.py b/tests/test_vocoder_melgan_discriminator.py index feafa60b..a4564b56 100644 --- a/tests/test_vocoder_melgan_discriminator.py +++ b/tests/test_vocoder_melgan_discriminator.py @@ -1,8 +1,8 @@ import numpy as np import torch -from mozilla_voice_tts.vocoder.models.melgan_discriminator import MelganDiscriminator -from mozilla_voice_tts.vocoder.models.melgan_multiscale_discriminator import MelganMultiscaleDiscriminator +from TTS.vocoder.models.melgan_discriminator import MelganDiscriminator +from TTS.vocoder.models.melgan_multiscale_discriminator import MelganMultiscaleDiscriminator def test_melgan_discriminator(): diff --git a/tests/test_vocoder_melgan_generator.py b/tests/test_vocoder_melgan_generator.py index c9cf5e2d..fedf6301 100644 --- a/tests/test_vocoder_melgan_generator.py +++ b/tests/test_vocoder_melgan_generator.py @@ -1,7 +1,7 @@ import numpy as np import torch -from mozilla_voice_tts.vocoder.models.melgan_generator import MelganGenerator +from TTS.vocoder.models.melgan_generator import MelganGenerator def test_melgan_generator(): model = MelganGenerator() diff --git a/tests/test_vocoder_parallel_wavegan_discriminator.py b/tests/test_vocoder_parallel_wavegan_discriminator.py index ac0b5393..b496e216 100644 --- a/tests/test_vocoder_parallel_wavegan_discriminator.py +++ b/tests/test_vocoder_parallel_wavegan_discriminator.py @@ -1,7 +1,7 @@ import numpy as np import torch -from mozilla_voice_tts.vocoder.models.parallel_wavegan_discriminator import ParallelWaveganDiscriminator, ResidualParallelWaveganDiscriminator +from TTS.vocoder.models.parallel_wavegan_discriminator import ParallelWaveganDiscriminator, ResidualParallelWaveganDiscriminator def test_pwgan_disciminator(): diff --git a/tests/test_vocoder_parallel_wavegan_generator.py b/tests/test_vocoder_parallel_wavegan_generator.py index 72af728f..9eed0eee 100644 --- a/tests/test_vocoder_parallel_wavegan_generator.py +++ b/tests/test_vocoder_parallel_wavegan_generator.py @@ -1,7 +1,7 @@ import numpy as np import torch -from mozilla_voice_tts.vocoder.models.parallel_wavegan_generator import ParallelWaveganGenerator +from TTS.vocoder.models.parallel_wavegan_generator import ParallelWaveganGenerator def test_pwgan_generator(): diff --git a/tests/test_vocoder_pqmf.py b/tests/test_vocoder_pqmf.py index 485e2f2b..1f141dd2 100644 --- a/tests/test_vocoder_pqmf.py +++ b/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 mozilla_voice_tts.vocoder.layers.pqmf import PQMF +from TTS.vocoder.layers.pqmf import PQMF TESTS_PATH = get_tests_path() diff --git a/tests/test_vocoder_rwd.py b/tests/test_vocoder_rwd.py index 266415db..424d3b49 100644 --- a/tests/test_vocoder_rwd.py +++ b/tests/test_vocoder_rwd.py @@ -1,7 +1,7 @@ import torch import numpy as np -from mozilla_voice_tts.vocoder.models.random_window_discriminator import RandomWindowDiscriminator +from TTS.vocoder.models.random_window_discriminator import RandomWindowDiscriminator def test_rwd(): diff --git a/tests/test_vocoder_tf_melgan_generator.py b/tests/test_vocoder_tf_melgan_generator.py index 5fdfc295..67968225 100644 --- a/tests/test_vocoder_tf_melgan_generator.py +++ b/tests/test_vocoder_tf_melgan_generator.py @@ -1,7 +1,7 @@ import numpy as np import tensorflow as tf -from mozilla_voice_tts.vocoder.tf.models.melgan_generator import MelganGenerator +from TTS.vocoder.tf.models.melgan_generator import MelganGenerator def test_melgan_generator(): diff --git a/tests/test_vocoder_tf_pqmf.py b/tests/test_vocoder_tf_pqmf.py index 851c0fb0..a1c4f692 100644 --- a/tests/test_vocoder_tf_pqmf.py +++ b/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 mozilla_voice_tts.vocoder.tf.layers.pqmf import PQMF +from TTS.vocoder.tf.layers.pqmf import PQMF TESTS_PATH = get_tests_path() diff --git a/tests/test_vocoder_train.sh b/tests/test_vocoder_train.sh index bba730dd..fa99b4bd 100755 --- a/tests/test_vocoder_train.sh +++ b/tests/test_vocoder_train.sh @@ -5,11 +5,11 @@ echo "$BASEDIR" # create run dir mkdir $BASEDIR/train_outputs # run training -CUDA_VISIBLE_DEVICES="" python mozilla_voice_tts/bin/train_vocoder.py --config_path $BASEDIR/inputs/test_vocoder_multiband_melgan_config.json +CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder.py --config_path $BASEDIR/inputs/test_vocoder_multiband_melgan_config.json # find the training folder LATEST_FOLDER=$(ls $BASEDIR/train_outputs/| sort | tail -1) echo $LATEST_FOLDER # continue the previous training -CUDA_VISIBLE_DEVICES="" python mozilla_voice_tts/bin/train_vocoder.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER +CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER # remove all the outputs rm -rf $BASEDIR/train_outputs/$LATEST_FOLDER