coqui-ai
/
TTS
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

rebranding and replacing import statements

pull/10/head
erogol 2020-08-04 10:51:19 +02:00
parent 868efa90b9
commit f35504f187
77 changed files with 240 additions and 239 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
mozilla_voice_tts/bin/compute_statistics.py
View File

@ -7,9 +7,9 @@ import argparse
import numpy as np
from tqdm import tqdm
from TTS.tts.datasets.preprocess import load_meta_data
from TTS.utils.io import load_config
from TTS.utils.audio import AudioProcessor
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
def main():
"""Run preprocessing process."""

8
mozilla_voice_tts/bin/convert_melgan_tflite.py
View File

@ -2,10 +2,10 @@
import argparse
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
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
parser = argparse.ArgumentParser()

10
mozilla_voice_tts/bin/convert_melgan_torch_to_tf.py
View File

@ -6,13 +6,13 @@ import tensorflow as tf
import torch
from fuzzywuzzy import fuzz
from TTS.utils.io import load_config
from TTS.vocoder.tf.utils.convert_torch_to_tf_utils import (
from mozilla_voice_tts.utils.io import load_config
from mozilla_voice_tts.vocoder.tf.utils.convert_torch_to_tf_utils import (
compare_torch_tf, convert_tf_name, transfer_weights_torch_to_tf)
from TTS.vocoder.tf.utils.generic_utils import \
from mozilla_voice_tts.vocoder.tf.utils.generic_utils import \
setup_generator as setup_tf_generator
from TTS.vocoder.tf.utils.io import save_checkpoint
from TTS.vocoder.utils.generic_utils import setup_generator
from mozilla_voice_tts.vocoder.tf.utils.io import save_checkpoint
from mozilla_voice_tts.vocoder.utils.generic_utils import setup_generator
# prevent GPU use
os.environ['CUDA_VISIBLE_DEVICES'] = ''

10
mozilla_voice_tts/bin/convert_tacotron2_tflite.py
View File

@ -2,11 +2,11 @@
import argparse
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
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
parser = argparse.ArgumentParser()

12
mozilla_voice_tts/bin/convert_tacotron2_torch_to_tf.py
View File

@ -11,13 +11,13 @@ import numpy as np
import tensorflow as tf
import torch
from fuzzywuzzy import fuzz
from TTS.tts.tf.models.tacotron2 import Tacotron2
from TTS.tts.tf.utils.convert_torch_to_tf_utils import (
from mozilla_voice_tts.tts.tf.models.tacotron2 import Tacotron2
from mozilla_voice_tts.tts.tf.utils.convert_torch_to_tf_utils import (
compare_torch_tf, convert_tf_name, transfer_weights_torch_to_tf)
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
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
sys.path.append('/home/erogol/Projects')
os.environ['CUDA_VISIBLE_DEVICES'] = ''

12
mozilla_voice_tts/bin/synthesize.py
View File

@ -10,12 +10,12 @@ import time
import torch
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
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
def tts(model, vocoder_model, text, CONFIG, use_cuda, ap, use_gl, speaker_id):

24
mozilla_voice_tts/bin/train_encoder.py
View File

@ -9,21 +9,21 @@ import traceback
import torch
from torch.utils.data import DataLoader
from TTS.speaker_encoder.dataset import MyDataset
from TTS.speaker_encoder.generic_utils import save_best_model
from TTS.speaker_encoder.loss import GE2ELoss
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.tts.utils.audio import AudioProcessor
from TTS.tts.utils.generic_utils import (create_experiment_folder,
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.loss import GE2ELoss
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.tts.utils.audio import AudioProcessor
from mozilla_voice_tts.tts.utils.generic_utils import (create_experiment_folder,
get_git_branch,
remove_experiment_folder,
set_init_dict)
from TTS.tts.utils.io import copy_config_file, load_config
from TTS.tts.utils.radam import RAdam
from TTS.tts.utils.tensorboard_logger import TensorboardLogger
from TTS.tts.utils.training import NoamLR, check_update
from mozilla_voice_tts.tts.utils.io import copy_config_file, load_config
from mozilla_voice_tts.tts.utils.radam import RAdam
from mozilla_voice_tts.tts.utils.tensorboard_logger import TensorboardLogger
from mozilla_voice_tts.tts.utils.training import NoamLR, check_update
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True

36
mozilla_voice_tts/bin/train_tts.py
View File

@ -11,29 +11,29 @@ import traceback
import numpy as np
import torch
from torch.utils.data import DataLoader
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,
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 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,
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 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,
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 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,
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)

24
mozilla_voice_tts/bin/train_vocoder.py
View File

@ -8,24 +8,24 @@ from inspect import signature
import torch
from torch.utils.data import DataLoader
from TTS.utils.audio import AudioProcessor
from TTS.utils.console_logger import ConsoleLogger
from TTS.utils.generic_utils import (KeepAverage, count_parameters,
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 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 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 distribute import (DistributedSampler, apply_gradient_allreduce,
# init_distributed, reduce_tensor)
from TTS.vocoder.layers.losses import DiscriminatorLoss, GeneratorLoss
from TTS.vocoder.utils.generic_utils import (check_config, plot_results,
from mozilla_voice_tts.vocoder.layers.losses import DiscriminatorLoss, GeneratorLoss
from mozilla_voice_tts.vocoder.utils.generic_utils import (check_config, plot_results,
setup_discriminator,
setup_generator)
from TTS.vocoder.utils.io import save_best_model, save_checkpoint
from mozilla_voice_tts.vocoder.utils.io import save_best_model, save_checkpoint
use_cuda, num_gpus = setup_torch_training_env(True, True)

2
mozilla_voice_tts/server/README.md
View File

@ -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 TTS.server.server
6. python -m mozilla_voice_tts.server.server
You can now open http://localhost:5002 in a browser

6
mozilla_voice_tts/server/server.py
View File

@ -3,7 +3,7 @@ import argparse
import os
from flask import Flask, request, render_template, send_file
from TTS.server.synthesizer import Synthesizer
from mozilla_voice_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 TTS.vocoder config file.')
parser.add_argument('--vocoder_checkpoint', type=str, default=None, help='path to TTS.vocoder checkpoint file.')
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('--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.')

14
mozilla_voice_tts/server/synthesizer.py
View File

@ -7,16 +7,16 @@ import torch
import yaml
import pysbd
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
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
# pylint: disable=unused-wildcard-import
# pylint: disable=wildcard-import
from TTS.tts.utils.synthesis import *
from mozilla_voice_tts.tts.utils.synthesis import *
from TTS.tts.utils.text import make_symbols, phonemes, symbols
from mozilla_voice_tts.tts.utils.text import make_symbols, phonemes, symbols
class Synthesizer(object):

6
mozilla_voice_tts/speaker_encoder/compute_embeddings.py
View File

@ -6,9 +6,9 @@ import numpy as np
from tqdm import tqdm
import torch
from TTS.speaker_encoder.model import SpeakerEncoder
from TTS.tts.utils.audio import AudioProcessor
from TTS.tts.utils.generic_utils import load_config
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
parser = argparse.ArgumentParser(
description='Compute embedding vectors for each wav file in a dataset. ')

2
mozilla_voice_tts/speaker_encoder/dataset.py
View File

@ -9,7 +9,7 @@ class MyDataset(Dataset):
num_utter_per_speaker=10, skip_speakers=False, verbose=False):
"""
Args:
ap (TTS.tts.utils.AudioProcessor): audio processor object.
ap (mozilla_voice_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.

6
mozilla_voice_tts/tts/datasets/TTSDataset.py
View File

@ -5,8 +5,8 @@ import torch
import random
from torch.utils.data import Dataset
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
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
class MyDataset(Dataset):
@ -30,7 +30,7 @@ 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 (TTS.tts.utils.AudioProcessor): audio processor object.
ap (mozilla_voice_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.

2
mozilla_voice_tts/tts/datasets/preprocess.py
View File

@ -2,7 +2,7 @@ import os
from glob import glob
import re
import sys
from TTS.tts.utils.generic_utils import split_dataset
from mozilla_voice_tts.tts.utils.generic_utils import split_dataset
def load_meta_data(datasets):

2
mozilla_voice_tts/tts/layers/losses.py
View File

@ -2,7 +2,7 @@ import numpy as np
import torch
from torch import nn
from torch.nn import functional
from TTS.tts.utils.generic_utils import sequence_mask
from mozilla_voice_tts.tts.utils.generic_utils import sequence_mask
class L1LossMasked(nn.Module):

6
mozilla_voice_tts/tts/models/tacotron.py
View File

@ -2,9 +2,9 @@
import torch
from torch import nn
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
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
class Tacotron(TacotronAbstract):

6
mozilla_voice_tts/tts/models/tacotron2.py
View File

@ -1,9 +1,9 @@
import torch
from torch import nn
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
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
# TODO: match function arguments with tacotron

2
mozilla_voice_tts/tts/models/tacotron_abstract.py
View File

@ -4,7 +4,7 @@ from abc import ABC, abstractmethod
import torch
from torch import nn
from TTS.tts.utils.generic_utils import sequence_mask
from mozilla_voice_tts.tts.utils.generic_utils import sequence_mask
class TacotronAbstract(ABC, nn.Module):

4
mozilla_voice_tts/tts/tf/layers/tacotron2.py
View File

@ -1,7 +1,7 @@
import tensorflow as tf
from tensorflow import keras
from TTS.tts.tf.utils.tf_utils import shape_list
from TTS.tts.tf.layers.common_layers import Prenet, Attention
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 tensorflow_addons.seq2seq import AttentionWrapper

4
mozilla_voice_tts/tts/tf/models/tacotron2.py
View File

@ -1,8 +1,8 @@
import tensorflow as tf
from tensorflow import keras
from TTS.tts.tf.layers.tacotron2 import Encoder, Decoder, Postnet
from TTS.tts.tf.utils.tf_utils import shape_list
from mozilla_voice_tts.tts.tf.layers.tacotron2 import Encoder, Decoder, Postnet
from mozilla_voice_tts.tts.tf.utils.tf_utils import shape_list
#pylint: disable=too-many-ancestors

2
mozilla_voice_tts/tts/tf/utils/generic_utils.py
View File

@ -78,7 +78,7 @@ 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('TTS.tts.tf.models.' + c.model.lower())
MyModel = importlib.import_module('mozilla_voice_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.')

2
mozilla_voice_tts/tts/utils/distribute.py
View File

@ -9,7 +9,7 @@ import torch.distributed as dist
from torch.utils.data.sampler import Sampler
from torch.autograd import Variable
from torch._utils import _flatten_dense_tensors, _unflatten_dense_tensors
from TTS.utils.generic_utils import create_experiment_folder
from mozilla_voice_tts.utils.generic_utils import create_experiment_folder
class DistributedSampler(Sampler):

6
mozilla_voice_tts/tts/utils/generic_utils.py
View File

@ -3,7 +3,7 @@ import importlib
import numpy as np
from collections import Counter
from TTS.utils.generic_utils import check_argument
from mozilla_voice_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):
print(" > Using model: {}".format(c.model))
MyModel = importlib.import_module('TTS.tts.models.' + c.model.lower())
MyModel = importlib.import_module('mozilla_voice_tts.tts.models.' + c.model.lower())
MyModel = getattr(MyModel, c.model)
if c.model.lower() in "tacotron":
model = MyModel(num_chars=num_chars,
@ -227,7 +227,7 @@ def check_config(c):
# dataloading
# pylint: disable=import-outside-toplevel
from TTS.tts.utils.text import cleaners
from mozilla_voice_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)

2
mozilla_voice_tts/tts/utils/speakers.py
View File

@ -1,7 +1,7 @@
import os
import json
from TTS.tts.datasets.preprocess import get_preprocessor_by_name
from mozilla_voice_tts.tts.datasets.preprocess import get_preprocessor_by_name
def make_speakers_json_path(out_path):

4
mozilla_voice_tts/tts/utils/synthesis.py
View File

@ -169,11 +169,11 @@ def synthesis(model,
"""Synthesize voice for the given text.
Args:
model (TTS.tts.models): model to synthesize.
model (mozilla_voice_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 (TTS.tts.utils.audio.AudioProcessor): audio processor to process
ap (mozilla_voice_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.

4
mozilla_voice_tts/tts/utils/text/__init__.py
View File

@ -4,8 +4,8 @@ import re
from packaging import version
import phonemizer
from phonemizer.phonemize import phonemize
from TTS.tts.utils.text import cleaners
from TTS.tts.utils.text.symbols import make_symbols, symbols, phonemes, _phoneme_punctuations, _bos, \
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, \
_eos
# Mappings from symbol to numeric ID and vice versa:

2
mozilla_voice_tts/tts/utils/visual.py
View File

@ -3,7 +3,7 @@ import librosa
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
from TTS.tts.utils.text import phoneme_to_sequence, sequence_to_phoneme
from mozilla_voice_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):

2
mozilla_voice_tts/utils/audio.py
View File

@ -4,7 +4,7 @@ import numpy as np
import scipy.io.wavfile
import scipy.signal
from TTS.tts.utils.data import StandardScaler
from mozilla_voice_tts.tts.utils.data import StandardScaler
class AudioProcessor(object):

2
mozilla_voice_tts/utils/console_logger.py
View File

@ -1,5 +1,5 @@
import datetime
from TTS.utils.io import AttrDict
from mozilla_voice_tts.utils.io import AttrDict
tcolors = AttrDict({

2
mozilla_voice_tts/vocoder/models/melgan_generator.py
View File

@ -2,7 +2,7 @@ import torch
from torch import nn
from torch.nn.utils import weight_norm
from TTS.vocoder.layers.melgan import ResidualStack
from mozilla_voice_tts.vocoder.layers.melgan import ResidualStack
class MelganGenerator(nn.Module):

2
mozilla_voice_tts/vocoder/models/melgan_multiscale_discriminator.py
View File

@ -1,6 +1,6 @@
from torch import nn
from TTS.vocoder.models.melgan_discriminator import MelganDiscriminator
from mozilla_voice_tts.vocoder.models.melgan_discriminator import MelganDiscriminator
class MelganMultiscaleDiscriminator(nn.Module):

4
mozilla_voice_tts/vocoder/models/multiband_melgan_generator.py
View File

@ -1,7 +1,7 @@
import torch
from TTS.vocoder.models.melgan_generator import MelganGenerator
from TTS.vocoder.layers.pqmf import PQMF
from mozilla_voice_tts.vocoder.models.melgan_generator import MelganGenerator
from mozilla_voice_tts.vocoder.layers.pqmf import PQMF
class MultibandMelganGenerator(MelganGenerator):

2
mozilla_voice_tts/vocoder/models/parallel_wavegan_discriminator.py
View File

@ -2,7 +2,7 @@ import math
import torch
from torch import nn
from TTS.vocoder.layers.parallel_wavegan import ResidualBlock
from mozilla_voice_tts.vocoder.layers.parallel_wavegan import ResidualBlock
class ParallelWaveganDiscriminator(nn.Module):

4
mozilla_voice_tts/vocoder/models/parallel_wavegan_generator.py
View File

@ -2,8 +2,8 @@ import math
import numpy as np
import torch
from TTS.vocoder.layers.parallel_wavegan import ResidualBlock
from TTS.vocoder.layers.upsample import ConvUpsample
from mozilla_voice_tts.vocoder.layers.parallel_wavegan import ResidualBlock
from mozilla_voice_tts.vocoder.layers.upsample import ConvUpsample
class ParallelWaveganGenerator(torch.nn.Module):

2
mozilla_voice_tts/vocoder/tf/models/melgan_generator.py
View File

@ -5,7 +5,7 @@ os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' # FATAL
logging.getLogger('tensorflow').setLevel(logging.FATAL)
import tensorflow as tf
from TTS.vocoder.tf.layers.melgan import ResidualStack, ReflectionPad1d
from mozilla_voice_tts.vocoder.tf.layers.melgan import ResidualStack, ReflectionPad1d
#pylint: disable=too-many-ancestors

4
mozilla_voice_tts/vocoder/tf/models/multiband_melgan_generator.py
View File

@ -1,7 +1,7 @@
import tensorflow as tf
from TTS.vocoder.tf.models.melgan_generator import MelganGenerator
from TTS.vocoder.tf.layers.pqmf import PQMF
from mozilla_voice_tts.vocoder.tf.models.melgan_generator import MelganGenerator
from mozilla_voice_tts.vocoder.tf.layers.pqmf import PQMF
#pylint: disable=too-many-ancestors
#pylint: disable=abstract-method

2
mozilla_voice_tts/vocoder/tf/utils/generic_utils.py
View File

@ -9,7 +9,7 @@ def to_camel(text):
def setup_generator(c):
print(" > Generator Model: {}".format(c.generator_model))
MyModel = importlib.import_module('TTS.vocoder.tf.models.' +
MyModel = importlib.import_module('mozilla_voice_tts.vocoder.tf.models.' +
c.generator_model.lower())
MyModel = getattr(MyModel, to_camel(c.generator_model))
if c.generator_model in 'melgan_generator':

8
mozilla_voice_tts/vocoder/utils/generic_utils.py
View File

@ -3,7 +3,7 @@ import importlib
import numpy as np
from matplotlib import pyplot as plt
from TTS.tts.utils.visual import plot_spectrogram
from mozilla_voice_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('TTS.vocoder.models.' +
MyModel = importlib.import_module('mozilla_voice_tts.vocoder.models.' +
c.generator_model.lower())
MyModel = getattr(MyModel, to_camel(c.generator_model))
if c.generator_model in 'melgan_generator':
@ -91,9 +91,9 @@ def setup_discriminator(c):
print(" > Discriminator Model: {}".format(c.discriminator_model))
if 'parallel_wavegan' in c.discriminator_model:
MyModel = importlib.import_module(
'TTS.vocoder.models.parallel_wavegan_discriminator')
'mozilla_voice_tts.vocoder.models.parallel_wavegan_discriminator')
else:
MyModel = importlib.import_module('TTS.vocoder.models.' +
MyModel = importlib.import_module('mozilla_voice_tts.vocoder.models.' +
c.discriminator_model.lower())
MyModel = getattr(MyModel, to_camel(c.discriminator_model.lower()))
if c.discriminator_model in 'random_window_discriminator':

6
notebooks/CheckSpectrograms.ipynb
View File

@ -16,9 +16,9 @@
"outputs": [],
"source": [
"%matplotlib inline\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\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\n",
"import glob \n",
"import IPython.display as ipd"
]

12
notebooks/DDC_TTS_and_MultiBand_MelGAN_Example.ipynb
View File

@ -154,11 +154,11 @@
"import time\n",
"import IPython\n",
"\n",
"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"
"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"
],
"execution_count": null,
"outputs": []
@ -280,7 +280,7 @@
"tags": []
},
"source": [
"from TTS.vocoder.utils.generic_utils import setup_generator\n",
"from mozilla_voice_tts.vocoder.utils.generic_utils import setup_generator\n",
"\n",
"# LOAD VOCODER MODEL\n",
"vocoder_model = setup_generator(VOCODER_CONFIG)\n",

12
notebooks/DDC_TTS_and_MultiBand_MelGAN_TFLite_Example.ipynb
View File

@ -1140,12 +1140,12 @@
"import time\n",
"import IPython\n",
"\n",
"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"
"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"
],
"execution_count": null,
"outputs": []

18
notebooks/DDC_TTS_and_MultiBand_MelGAN_TF_Example.ipynb
View File

@ -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 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 mozilla_voice_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 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"
"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"
],
"execution_count": null,
"outputs": []
@ -270,8 +270,8 @@
"outputId": "2cc3deae-144f-4465-da3b-98628d948506"
},
"source": [
"from TTS.vocoder.tf.utils.generic_utils import setup_generator\n",
"from TTS.vocoder.tf.utils.io import load_checkpoint\n",
"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",
"\n",
"# LOAD VOCODER MODEL\n",
"vocoder_model = setup_generator(VOCODER_CONFIG)\n",

12
notebooks/DDC_TTS_and_ParallelWaveGAN_Example.ipynb
View File

@ -154,11 +154,11 @@
"import time\n",
"import IPython\n",
"\n",
"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"
"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"
],
"execution_count": null,
"outputs": []
@ -280,7 +280,7 @@
"tags": []
},
"source": [
"from TTS.vocoder.utils.generic_utils import setup_generator\n",
"from mozilla_voice_tts.vocoder.utils.generic_utils import setup_generator\n",
"\n",
"# LOAD VOCODER MODEL\n",
"vocoder_model = setup_generator(VOCODER_CONFIG)\n",

14
notebooks/ExtractTTSpectrogram.ipynb
View File

@ -22,12 +22,12 @@
"import numpy as np\n",
"from tqdm import tqdm as tqdm\n",
"from torch.utils.data import DataLoader\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",
"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",
"\n",
"%matplotlib inline\n",
"\n",
@ -108,7 +108,7 @@
"metadata": {},
"outputs": [],
"source": [
"preprocessor = importlib.import_module('TTS.tts.datasets.preprocess')\n",
"preprocessor = importlib.import_module('mozilla_voice_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",

18
notebooks/TestAttention.ipynb
View File

@ -36,14 +36,14 @@
"import librosa\n",
"import librosa.display\n",
"\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",
"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",
"\n",
"import IPython\n",
"from IPython.display import Audio\n",
@ -96,7 +96,7 @@
"outputs": [],
"source": [
"# LOAD TTS MODEL\n",
"from TTS.tts.utils.text.symbols import make_symbols, symbols, phonemes\n",
"from mozilla_voice_tts.tts.utils.text.symbols import make_symbols, symbols, phonemes\n",
"\n",
"# multi speaker \n",
"if CONFIG.use_speaker_embedding:\n",

12
notebooks/Tutorial_Converting_PyTorch_to_TF_to_TFlite.ipynb
View File

@ -276,12 +276,12 @@
"import time\n",
"import IPython\n",
"\n",
"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"
"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"
],
"execution_count": null,
"outputs": []

2
notebooks/dataset_analysis/AnalyzeDataset-Copy1.ipynb
View File

@ -31,7 +31,7 @@
"from multiprocessing import Pool\n",
"from matplotlib import pylab as plt\n",
"from collections import Counter\n",
"from TTS.tts.datasets.preprocess import *\n",
"from mozilla_voice_tts.tts.datasets.preprocess import *\n",
"%matplotlib inline"
]
},

2
notebooks/dataset_analysis/AnalyzeDataset.ipynb
View File

@ -27,7 +27,7 @@
"from multiprocessing import Pool\n",
"from matplotlib import pylab as plt\n",
"from collections import Counter\n",
"from TTS.tts.datasets.preprocess import *\n",
"from mozilla_voice_tts.tts.datasets.preprocess import *\n",
"%matplotlib inline"
]
},

4
tests/generic_utils_text.py
View File

@ -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'

1
tests/inputs/test_train_config.json
View File

@ -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,

2
tests/outputs/dummy_model_config.json
View File

@ -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.

2
tests/symbols_tests.py
View File

@ -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

4
tests/test_audio.py
View File

@ -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")

10
tests/test_demo_server.py
View File

@ -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):

6
tests/test_encoder.py
View File

@ -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()

6
tests/test_layers.py
View File

@ -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

8
tests/test_loader.py
View File

@ -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

2
tests/test_preprocessors.py
View File

@ -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):

4
tests/test_server_package.sh
View File

@ -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...'

6
tests/test_tacotron2_model.py
View File

@ -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

6
tests/test_tacotron2_tf_model.py
View File

@ -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

6
tests/test_tacotron_model.py
View File

@ -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

4
tests/test_text_processing.py
View File

@ -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'))

4
tests/test_tts_train.sh
View File

@ -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/

8
tests/test_vocoder_datasets.py
View File

@ -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/")

6
tests/test_vocoder_losses.py
View File

@ -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()

4
tests/test_vocoder_melgan_discriminator.py
View File

@ -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():

2
tests/test_vocoder_melgan_generator.py
View File

@ -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()

2
tests/test_vocoder_parallel_wavegan_discriminator.py
View File

@ -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():

2
tests/test_vocoder_parallel_wavegan_generator.py
View File

@ -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():

2
tests/test_vocoder_pqmf.py
View File

@ -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()

2
tests/test_vocoder_rwd.py
View File

@ -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():

2
tests/test_vocoder_tf_melgan_generator.py
View File

@ -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():

2
tests/test_vocoder_tf_pqmf.py
View File

@ -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()

4
tests/test_vocoder_train.sh
View File

@ -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/