From 71a1907f4c3a8c616d2ab7799572a142d7ebe8b8 Mon Sep 17 00:00:00 2001 From: Edresson Casanova Date: Mon, 28 Feb 2022 15:28:29 -0300 Subject: [PATCH] Rename Speaker encoder module to encoder --- TTS/bin/train_encoder.py | 10 +++++----- TTS/speaker_encoder/dataset.py | 2 +- TTS/speaker_encoder/models/lstm.py | 2 +- TTS/speaker_encoder/utils/generic_utils.py | 4 ++-- TTS/tts/utils/speakers.py | 2 +- tests/aux_tests/test_speaker_encoder.py | 6 +++--- tests/aux_tests/test_speaker_encoder_train.py | 2 +- tests/aux_tests/test_speaker_manager.py | 4 ++-- tests/tts_tests/test_vits.py | 2 +- 9 files changed, 17 insertions(+), 17 deletions(-) diff --git a/TTS/bin/train_encoder.py b/TTS/bin/train_encoder.py index b7424698..dc160762 100644 --- a/TTS/bin/train_encoder.py +++ b/TTS/bin/train_encoder.py @@ -10,11 +10,11 @@ import torch from torch.utils.data import DataLoader from trainer.torch import NoamLR -from TTS.speaker_encoder.dataset import SpeakerEncoderDataset -from TTS.speaker_encoder.losses import AngleProtoLoss, GE2ELoss, SoftmaxAngleProtoLoss -from TTS.speaker_encoder.utils.generic_utils import save_best_model, setup_speaker_encoder_model -from TTS.speaker_encoder.utils.training import init_training -from TTS.speaker_encoder.utils.visual import plot_embeddings +from TTS.encoder.dataset import SpeakerEncoderDataset +from TTS.encoder.losses import AngleProtoLoss, GE2ELoss, SoftmaxAngleProtoLoss +from TTS.encoder.utils.generic_utils import save_best_model, setup_speaker_encoder_model +from TTS.encoder.utils.training import init_training +from TTS.encoder.utils.visual import plot_embeddings from TTS.tts.datasets import load_tts_samples from TTS.utils.audio import AudioProcessor from TTS.utils.generic_utils import count_parameters, remove_experiment_folder, set_init_dict diff --git a/TTS/speaker_encoder/dataset.py b/TTS/speaker_encoder/dataset.py index 07fa9246..fddad6d3 100644 --- a/TTS/speaker_encoder/dataset.py +++ b/TTS/speaker_encoder/dataset.py @@ -4,7 +4,7 @@ import numpy as np import torch from torch.utils.data import Dataset -from TTS.speaker_encoder.utils.generic_utils import AugmentWAV, Storage +from TTS.encoder.utils.generic_utils import AugmentWAV, Storage class SpeakerEncoderDataset(Dataset): diff --git a/TTS/speaker_encoder/models/lstm.py b/TTS/speaker_encoder/models/lstm.py index ec394cdb..dfba53cc 100644 --- a/TTS/speaker_encoder/models/lstm.py +++ b/TTS/speaker_encoder/models/lstm.py @@ -3,7 +3,7 @@ import torch import torchaudio from torch import nn -from TTS.speaker_encoder.models.resnet import PreEmphasis +from TTS.encoder.models.resnet import PreEmphasis from TTS.utils.io import load_fsspec diff --git a/TTS/speaker_encoder/utils/generic_utils.py b/TTS/speaker_encoder/utils/generic_utils.py index 4ab4e923..141b91fb 100644 --- a/TTS/speaker_encoder/utils/generic_utils.py +++ b/TTS/speaker_encoder/utils/generic_utils.py @@ -8,8 +8,8 @@ from multiprocessing import Manager import numpy as np from scipy import signal -from TTS.speaker_encoder.models.lstm import LSTMSpeakerEncoder -from TTS.speaker_encoder.models.resnet import ResNetSpeakerEncoder +from TTS.encoder.models.lstm import LSTMSpeakerEncoder +from TTS.encoder.models.resnet import ResNetSpeakerEncoder from TTS.utils.io import save_fsspec diff --git a/TTS/tts/utils/speakers.py b/TTS/tts/utils/speakers.py index c15a3abf..c2da7eb5 100644 --- a/TTS/tts/utils/speakers.py +++ b/TTS/tts/utils/speakers.py @@ -9,7 +9,7 @@ import torch from coqpit import Coqpit from TTS.config import get_from_config_or_model_args_with_default, load_config -from TTS.speaker_encoder.utils.generic_utils import setup_speaker_encoder_model +from TTS.encoder.utils.generic_utils import setup_speaker_encoder_model from TTS.utils.audio import AudioProcessor diff --git a/tests/aux_tests/test_speaker_encoder.py b/tests/aux_tests/test_speaker_encoder.py index 97b3b92f..f2875cc1 100644 --- a/tests/aux_tests/test_speaker_encoder.py +++ b/tests/aux_tests/test_speaker_encoder.py @@ -3,9 +3,9 @@ import unittest import torch as T from tests import get_tests_input_path -from TTS.speaker_encoder.losses import AngleProtoLoss, GE2ELoss, SoftmaxAngleProtoLoss -from TTS.speaker_encoder.models.lstm import LSTMSpeakerEncoder -from TTS.speaker_encoder.models.resnet import ResNetSpeakerEncoder +from TTS.encoder.losses import AngleProtoLoss, GE2ELoss, SoftmaxAngleProtoLoss +from TTS.encoder.models.lstm import LSTMSpeakerEncoder +from TTS.encoder.models.resnet import ResNetSpeakerEncoder file_path = get_tests_input_path() diff --git a/tests/aux_tests/test_speaker_encoder_train.py b/tests/aux_tests/test_speaker_encoder_train.py index 7901fe5a..fcbbd8e3 100644 --- a/tests/aux_tests/test_speaker_encoder_train.py +++ b/tests/aux_tests/test_speaker_encoder_train.py @@ -4,7 +4,7 @@ import shutil from tests import get_device_id, get_tests_output_path, run_cli from TTS.config.shared_configs import BaseAudioConfig -from TTS.speaker_encoder.speaker_encoder_config import SpeakerEncoderConfig +from TTS.encoder.speaker_encoder_config import SpeakerEncoderConfig def run_test_train(): diff --git a/tests/aux_tests/test_speaker_manager.py b/tests/aux_tests/test_speaker_manager.py index fff49b13..5fafb56a 100644 --- a/tests/aux_tests/test_speaker_manager.py +++ b/tests/aux_tests/test_speaker_manager.py @@ -6,8 +6,8 @@ import torch from tests import get_tests_input_path from TTS.config import load_config -from TTS.speaker_encoder.utils.generic_utils import setup_speaker_encoder_model -from TTS.speaker_encoder.utils.io import save_checkpoint +from TTS.encoder.utils.generic_utils import setup_speaker_encoder_model +from TTS.encoder.utils.io import save_checkpoint from TTS.tts.utils.speakers import SpeakerManager from TTS.utils.audio import AudioProcessor diff --git a/tests/tts_tests/test_vits.py b/tests/tts_tests/test_vits.py index 384234e5..81d2ebbd 100644 --- a/tests/tts_tests/test_vits.py +++ b/tests/tts_tests/test_vits.py @@ -7,7 +7,7 @@ from trainer.logging.tensorboard_logger import TensorboardLogger from tests import assertHasAttr, assertHasNotAttr, get_tests_data_path, get_tests_input_path, get_tests_output_path from TTS.config import load_config -from TTS.speaker_encoder.utils.generic_utils import setup_speaker_encoder_model +from TTS.encoder.utils.generic_utils import setup_speaker_encoder_model from TTS.tts.configs.vits_config import VitsConfig from TTS.tts.models.vits import Vits, VitsArgs, amp_to_db, db_to_amp, load_audio, spec_to_mel, wav_to_mel, wav_to_spec from TTS.tts.utils.speakers import SpeakerManager