From da82d55329ec287e48d115986f2cc3a724f1275f Mon Sep 17 00:00:00 2001
From: Enno Hermann <enno.hermann@idiap.ch>
Date: Thu, 27 Jun 2024 11:10:34 +0200
Subject: [PATCH] refactor: use load_fsspec from trainer

Made automatically with:
rg "from TTS.utils.io import load_fsspec" --files-with-matches | xargs sed -i 's/from TTS.utils.io import load_fsspec/from trainer.io import load_fsspec/g'
---
 TTS/encoder/models/base_encoder.py                       | 2 +-
 TTS/tts/layers/xtts/hifigan_decoder.py                   | 2 +-
 TTS/tts/layers/xtts/trainer/gpt_trainer.py               | 2 +-
 TTS/tts/models/align_tts.py                              | 2 +-
 TTS/tts/models/base_tacotron.py                          | 2 +-
 TTS/tts/models/delightful_tts.py                         | 2 +-
 TTS/tts/models/forward_tts.py                            | 2 +-
 TTS/tts/models/glow_tts.py                               | 2 +-
 TTS/tts/models/neuralhmm_tts.py                          | 2 +-
 TTS/tts/models/overflow.py                               | 2 +-
 TTS/tts/models/vits.py                                   | 2 +-
 TTS/tts/models/xtts.py                                   | 2 +-
 TTS/vc/models/freevc.py                                  | 2 +-
 TTS/vc/modules/freevc/speaker_encoder/speaker_encoder.py | 2 +-
 TTS/vocoder/models/gan.py                                | 2 +-
 TTS/vocoder/models/hifigan_generator.py                  | 3 +--
 TTS/vocoder/models/melgan_generator.py                   | 2 +-
 TTS/vocoder/models/parallel_wavegan_generator.py         | 2 +-
 TTS/vocoder/models/wavegrad.py                           | 2 +-
 TTS/vocoder/models/wavernn.py                            | 2 +-
 20 files changed, 20 insertions(+), 21 deletions(-)

diff --git a/TTS/encoder/models/base_encoder.py b/TTS/encoder/models/base_encoder.py
index 37406246..f7137c21 100644
--- a/TTS/encoder/models/base_encoder.py
+++ b/TTS/encoder/models/base_encoder.py
@@ -5,10 +5,10 @@ import torch
 import torchaudio
 from coqpit import Coqpit
 from torch import nn
+from trainer.io import load_fsspec
 
 from TTS.encoder.losses import AngleProtoLoss, GE2ELoss, SoftmaxAngleProtoLoss
 from TTS.utils.generic_utils import set_init_dict
-from TTS.utils.io import load_fsspec
 
 logger = logging.getLogger(__name__)
 
diff --git a/TTS/tts/layers/xtts/hifigan_decoder.py b/TTS/tts/layers/xtts/hifigan_decoder.py
index 9160529b..b6032e55 100644
--- a/TTS/tts/layers/xtts/hifigan_decoder.py
+++ b/TTS/tts/layers/xtts/hifigan_decoder.py
@@ -7,8 +7,8 @@ from torch.nn import Conv1d, ConvTranspose1d
 from torch.nn import functional as F
 from torch.nn.utils.parametrizations import weight_norm
 from torch.nn.utils.parametrize import remove_parametrizations
+from trainer.io import load_fsspec
 
-from TTS.utils.io import load_fsspec
 from TTS.vocoder.models.hifigan_generator import get_padding
 
 logger = logging.getLogger(__name__)
diff --git a/TTS/tts/layers/xtts/trainer/gpt_trainer.py b/TTS/tts/layers/xtts/trainer/gpt_trainer.py
index 0f161324..04d12377 100644
--- a/TTS/tts/layers/xtts/trainer/gpt_trainer.py
+++ b/TTS/tts/layers/xtts/trainer/gpt_trainer.py
@@ -7,6 +7,7 @@ import torch.nn as nn
 import torchaudio
 from coqpit import Coqpit
 from torch.utils.data import DataLoader
+from trainer.io import load_fsspec
 from trainer.torch import DistributedSampler
 from trainer.trainer_utils import get_optimizer, get_scheduler
 
@@ -18,7 +19,6 @@ from TTS.tts.layers.xtts.tokenizer import VoiceBpeTokenizer
 from TTS.tts.layers.xtts.trainer.dataset import XTTSDataset
 from TTS.tts.models.base_tts import BaseTTS
 from TTS.tts.models.xtts import Xtts, XttsArgs, XttsAudioConfig
-from TTS.utils.io import load_fsspec
 
 logger = logging.getLogger(__name__)
 
diff --git a/TTS/tts/models/align_tts.py b/TTS/tts/models/align_tts.py
index 18b9cde3..2d27a578 100644
--- a/TTS/tts/models/align_tts.py
+++ b/TTS/tts/models/align_tts.py
@@ -4,6 +4,7 @@ from typing import Dict, List, Union
 import torch
 from coqpit import Coqpit
 from torch import nn
+from trainer.io import load_fsspec
 
 from TTS.tts.layers.align_tts.mdn import MDNBlock
 from TTS.tts.layers.feed_forward.decoder import Decoder
@@ -15,7 +16,6 @@ from TTS.tts.utils.helpers import generate_path, maximum_path, sequence_mask
 from TTS.tts.utils.speakers import SpeakerManager
 from TTS.tts.utils.text.tokenizer import TTSTokenizer
 from TTS.tts.utils.visual import plot_alignment, plot_spectrogram
-from TTS.utils.io import load_fsspec
 
 
 @dataclass
diff --git a/TTS/tts/models/base_tacotron.py b/TTS/tts/models/base_tacotron.py
index 58b0e2c6..79cdf1a7 100644
--- a/TTS/tts/models/base_tacotron.py
+++ b/TTS/tts/models/base_tacotron.py
@@ -6,6 +6,7 @@ from typing import Dict, Tuple
 import torch
 from coqpit import Coqpit
 from torch import nn
+from trainer.io import load_fsspec
 
 from TTS.tts.layers.losses import TacotronLoss
 from TTS.tts.models.base_tts import BaseTTS
@@ -15,7 +16,6 @@ from TTS.tts.utils.synthesis import synthesis
 from TTS.tts.utils.text.tokenizer import TTSTokenizer
 from TTS.tts.utils.visual import plot_alignment, plot_spectrogram
 from TTS.utils.generic_utils import format_aux_input
-from TTS.utils.io import load_fsspec
 from TTS.utils.training import gradual_training_scheduler
 
 logger = logging.getLogger(__name__)
diff --git a/TTS/tts/models/delightful_tts.py b/TTS/tts/models/delightful_tts.py
index 4230fcc3..a938a3a4 100644
--- a/TTS/tts/models/delightful_tts.py
+++ b/TTS/tts/models/delightful_tts.py
@@ -16,6 +16,7 @@ from torch.cuda.amp.autocast_mode import autocast
 from torch.nn import functional as F
 from torch.utils.data import DataLoader
 from torch.utils.data.sampler import WeightedRandomSampler
+from trainer.io import load_fsspec
 from trainer.torch import DistributedSampler, DistributedSamplerWrapper
 from trainer.trainer_utils import get_optimizer, get_scheduler
 
@@ -32,7 +33,6 @@ from TTS.utils.audio.numpy_transforms import build_mel_basis, compute_f0
 from TTS.utils.audio.numpy_transforms import db_to_amp as db_to_amp_numpy
 from TTS.utils.audio.numpy_transforms import mel_to_wav as mel_to_wav_numpy
 from TTS.utils.audio.processor import AudioProcessor
-from TTS.utils.io import load_fsspec
 from TTS.vocoder.layers.losses import MultiScaleSTFTLoss
 from TTS.vocoder.models.hifigan_generator import HifiganGenerator
 from TTS.vocoder.utils.generic_utils import plot_results
diff --git a/TTS/tts/models/forward_tts.py b/TTS/tts/models/forward_tts.py
index b108a554..4b74462d 100644
--- a/TTS/tts/models/forward_tts.py
+++ b/TTS/tts/models/forward_tts.py
@@ -6,6 +6,7 @@ import torch
 from coqpit import Coqpit
 from torch import nn
 from torch.cuda.amp.autocast_mode import autocast
+from trainer.io import load_fsspec
 
 from TTS.tts.layers.feed_forward.decoder import Decoder
 from TTS.tts.layers.feed_forward.encoder import Encoder
@@ -17,7 +18,6 @@ from TTS.tts.utils.helpers import average_over_durations, generate_path, maximum
 from TTS.tts.utils.speakers import SpeakerManager
 from TTS.tts.utils.text.tokenizer import TTSTokenizer
 from TTS.tts.utils.visual import plot_alignment, plot_avg_energy, plot_avg_pitch, plot_spectrogram
-from TTS.utils.io import load_fsspec
 
 logger = logging.getLogger(__name__)
 
diff --git a/TTS/tts/models/glow_tts.py b/TTS/tts/models/glow_tts.py
index a4ae0121..64954d28 100644
--- a/TTS/tts/models/glow_tts.py
+++ b/TTS/tts/models/glow_tts.py
@@ -7,6 +7,7 @@ from coqpit import Coqpit
 from torch import nn
 from torch.cuda.amp.autocast_mode import autocast
 from torch.nn import functional as F
+from trainer.io import load_fsspec
 
 from TTS.tts.configs.glow_tts_config import GlowTTSConfig
 from TTS.tts.layers.glow_tts.decoder import Decoder
@@ -17,7 +18,6 @@ from TTS.tts.utils.speakers import SpeakerManager
 from TTS.tts.utils.synthesis import synthesis
 from TTS.tts.utils.text.tokenizer import TTSTokenizer
 from TTS.tts.utils.visual import plot_alignment, plot_spectrogram
-from TTS.utils.io import load_fsspec
 
 logger = logging.getLogger(__name__)
 
diff --git a/TTS/tts/models/neuralhmm_tts.py b/TTS/tts/models/neuralhmm_tts.py
index d5bd9d13..277369e6 100644
--- a/TTS/tts/models/neuralhmm_tts.py
+++ b/TTS/tts/models/neuralhmm_tts.py
@@ -5,6 +5,7 @@ from typing import Dict, List, Union
 import torch
 from coqpit import Coqpit
 from torch import nn
+from trainer.io import load_fsspec
 from trainer.logging.tensorboard_logger import TensorboardLogger
 
 from TTS.tts.layers.overflow.common_layers import Encoder, OverflowUtils
@@ -18,7 +19,6 @@ from TTS.tts.utils.speakers import SpeakerManager
 from TTS.tts.utils.text.tokenizer import TTSTokenizer
 from TTS.tts.utils.visual import plot_alignment, plot_spectrogram
 from TTS.utils.generic_utils import format_aux_input
-from TTS.utils.io import load_fsspec
 
 logger = logging.getLogger(__name__)
 
diff --git a/TTS/tts/models/overflow.py b/TTS/tts/models/overflow.py
index 0218d045..b05b7500 100644
--- a/TTS/tts/models/overflow.py
+++ b/TTS/tts/models/overflow.py
@@ -5,6 +5,7 @@ from typing import Dict, List, Union
 import torch
 from coqpit import Coqpit
 from torch import nn
+from trainer.io import load_fsspec
 from trainer.logging.tensorboard_logger import TensorboardLogger
 
 from TTS.tts.layers.overflow.common_layers import Encoder, OverflowUtils
@@ -19,7 +20,6 @@ from TTS.tts.utils.speakers import SpeakerManager
 from TTS.tts.utils.text.tokenizer import TTSTokenizer
 from TTS.tts.utils.visual import plot_alignment, plot_spectrogram
 from TTS.utils.generic_utils import format_aux_input
-from TTS.utils.io import load_fsspec
 
 logger = logging.getLogger(__name__)
 
diff --git a/TTS/tts/models/vits.py b/TTS/tts/models/vits.py
index 25521337..b014e4fd 100644
--- a/TTS/tts/models/vits.py
+++ b/TTS/tts/models/vits.py
@@ -16,6 +16,7 @@ from torch.cuda.amp.autocast_mode import autocast
 from torch.nn import functional as F
 from torch.utils.data import DataLoader
 from torch.utils.data.sampler import WeightedRandomSampler
+from trainer.io import load_fsspec
 from trainer.torch import DistributedSampler, DistributedSamplerWrapper
 from trainer.trainer_utils import get_optimizer, get_scheduler
 
@@ -34,7 +35,6 @@ from TTS.tts.utils.synthesis import synthesis
 from TTS.tts.utils.text.characters import BaseCharacters, BaseVocabulary, _characters, _pad, _phonemes, _punctuations
 from TTS.tts.utils.text.tokenizer import TTSTokenizer
 from TTS.tts.utils.visual import plot_alignment
-from TTS.utils.io import load_fsspec
 from TTS.utils.samplers import BucketBatchSampler
 from TTS.vocoder.models.hifigan_generator import HifiganGenerator
 from TTS.vocoder.utils.generic_utils import plot_results
diff --git a/TTS/tts/models/xtts.py b/TTS/tts/models/xtts.py
index e6d245a0..fa320aac 100644
--- a/TTS/tts/models/xtts.py
+++ b/TTS/tts/models/xtts.py
@@ -7,6 +7,7 @@ import torch
 import torch.nn.functional as F
 import torchaudio
 from coqpit import Coqpit
+from trainer.io import load_fsspec
 
 from TTS.tts.layers.xtts.gpt import GPT
 from TTS.tts.layers.xtts.hifigan_decoder import HifiDecoder
@@ -14,7 +15,6 @@ from TTS.tts.layers.xtts.stream_generator import init_stream_support
 from TTS.tts.layers.xtts.tokenizer import VoiceBpeTokenizer, split_sentence
 from TTS.tts.layers.xtts.xtts_manager import LanguageManager, SpeakerManager
 from TTS.tts.models.base_tts import BaseTTS
-from TTS.utils.io import load_fsspec
 
 logger = logging.getLogger(__name__)
 
diff --git a/TTS/vc/models/freevc.py b/TTS/vc/models/freevc.py
index 7746572f..e5cfdc1e 100644
--- a/TTS/vc/models/freevc.py
+++ b/TTS/vc/models/freevc.py
@@ -11,12 +11,12 @@ from torch.nn import functional as F
 from torch.nn.utils import spectral_norm
 from torch.nn.utils.parametrizations import weight_norm
 from torch.nn.utils.parametrize import remove_parametrizations
+from trainer.io import load_fsspec
 
 import TTS.vc.modules.freevc.commons as commons
 import TTS.vc.modules.freevc.modules as modules
 from TTS.tts.utils.helpers import sequence_mask
 from TTS.tts.utils.speakers import SpeakerManager
-from TTS.utils.io import load_fsspec
 from TTS.vc.configs.freevc_config import FreeVCConfig
 from TTS.vc.models.base_vc import BaseVC
 from TTS.vc.modules.freevc.commons import init_weights
diff --git a/TTS/vc/modules/freevc/speaker_encoder/speaker_encoder.py b/TTS/vc/modules/freevc/speaker_encoder/speaker_encoder.py
index 2636400b..294bf322 100644
--- a/TTS/vc/modules/freevc/speaker_encoder/speaker_encoder.py
+++ b/TTS/vc/modules/freevc/speaker_encoder/speaker_encoder.py
@@ -5,8 +5,8 @@ from typing import List, Union
 import numpy as np
 import torch
 from torch import nn
+from trainer.io import load_fsspec
 
-from TTS.utils.io import load_fsspec
 from TTS.vc.modules.freevc.speaker_encoder import audio
 from TTS.vc.modules.freevc.speaker_encoder.hparams import (
     mel_n_channels,
diff --git a/TTS/vocoder/models/gan.py b/TTS/vocoder/models/gan.py
index 9b6508d8..8792950a 100644
--- a/TTS/vocoder/models/gan.py
+++ b/TTS/vocoder/models/gan.py
@@ -7,10 +7,10 @@ from coqpit import Coqpit
 from torch import nn
 from torch.utils.data import DataLoader
 from torch.utils.data.distributed import DistributedSampler
+from trainer.io import load_fsspec
 from trainer.trainer_utils import get_optimizer, get_scheduler
 
 from TTS.utils.audio import AudioProcessor
-from TTS.utils.io import load_fsspec
 from TTS.vocoder.datasets.gan_dataset import GANDataset
 from TTS.vocoder.layers.losses import DiscriminatorLoss, GeneratorLoss
 from TTS.vocoder.models import setup_discriminator, setup_generator
diff --git a/TTS/vocoder/models/hifigan_generator.py b/TTS/vocoder/models/hifigan_generator.py
index 083ce344..afdd59a8 100644
--- a/TTS/vocoder/models/hifigan_generator.py
+++ b/TTS/vocoder/models/hifigan_generator.py
@@ -7,8 +7,7 @@ from torch.nn import Conv1d, ConvTranspose1d
 from torch.nn import functional as F
 from torch.nn.utils.parametrizations import weight_norm
 from torch.nn.utils.parametrize import remove_parametrizations
-
-from TTS.utils.io import load_fsspec
+from trainer.io import load_fsspec
 
 logger = logging.getLogger(__name__)
 
diff --git a/TTS/vocoder/models/melgan_generator.py b/TTS/vocoder/models/melgan_generator.py
index bb3fee78..03c971af 100644
--- a/TTS/vocoder/models/melgan_generator.py
+++ b/TTS/vocoder/models/melgan_generator.py
@@ -1,8 +1,8 @@
 import torch
 from torch import nn
 from torch.nn.utils.parametrizations import weight_norm
+from trainer.io import load_fsspec
 
-from TTS.utils.io import load_fsspec
 from TTS.vocoder.layers.melgan import ResidualStack
 
 
diff --git a/TTS/vocoder/models/parallel_wavegan_generator.py b/TTS/vocoder/models/parallel_wavegan_generator.py
index 96684d2a..6a4d4ca6 100644
--- a/TTS/vocoder/models/parallel_wavegan_generator.py
+++ b/TTS/vocoder/models/parallel_wavegan_generator.py
@@ -4,8 +4,8 @@ import math
 import numpy as np
 import torch
 from torch.nn.utils.parametrize import remove_parametrizations
+from trainer.io import load_fsspec
 
-from TTS.utils.io import load_fsspec
 from TTS.vocoder.layers.parallel_wavegan import ResidualBlock
 from TTS.vocoder.layers.upsample import ConvUpsample
 
diff --git a/TTS/vocoder/models/wavegrad.py b/TTS/vocoder/models/wavegrad.py
index 70d9edb3..c49abd22 100644
--- a/TTS/vocoder/models/wavegrad.py
+++ b/TTS/vocoder/models/wavegrad.py
@@ -9,9 +9,9 @@ from torch.nn.utils.parametrizations import weight_norm
 from torch.nn.utils.parametrize import remove_parametrizations
 from torch.utils.data import DataLoader
 from torch.utils.data.distributed import DistributedSampler
+from trainer.io import load_fsspec
 from trainer.trainer_utils import get_optimizer, get_scheduler
 
-from TTS.utils.io import load_fsspec
 from TTS.vocoder.datasets import WaveGradDataset
 from TTS.vocoder.layers.wavegrad import Conv1d, DBlock, FiLM, UBlock
 from TTS.vocoder.models.base_vocoder import BaseVocoder
diff --git a/TTS/vocoder/models/wavernn.py b/TTS/vocoder/models/wavernn.py
index 901afdff..723f18dd 100644
--- a/TTS/vocoder/models/wavernn.py
+++ b/TTS/vocoder/models/wavernn.py
@@ -10,11 +10,11 @@ from coqpit import Coqpit
 from torch import nn
 from torch.utils.data import DataLoader
 from torch.utils.data.distributed import DistributedSampler
+from trainer.io import load_fsspec
 
 from TTS.tts.utils.visual import plot_spectrogram
 from TTS.utils.audio import AudioProcessor
 from TTS.utils.audio.numpy_transforms import mulaw_decode
-from TTS.utils.io import load_fsspec
 from TTS.vocoder.datasets.wavernn_dataset import WaveRNNDataset
 from TTS.vocoder.layers.losses import WaveRNNLoss
 from TTS.vocoder.models.base_vocoder import BaseVocoder