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

Get rid of some star imports

This commit is contained in:
Aarni Koskela 2023-09-26 23:08:45 +03:00
parent 859283a734
commit 72ac2bfa09
4 changed files with 19 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
TTS/vc/modules/freevc/speaker_encoder/audio.py
View File

@ -7,7 +7,13 @@ import librosa
import numpy as np import numpy as np
from scipy.ndimage.morphology import binary_dilation from scipy.ndimage.morphology import binary_dilation
from TTS.vc.modules.freevc.speaker_encoder.hparams import * from TTS.vc.modules.freevc.speaker_encoder.hparams import (
audio_norm_target_dBFS,
mel_n_channels,
mel_window_length,
mel_window_step,
sampling_rate,
)
int16_max = (2**15) - 1 int16_max = (2**15) - 1

10
TTS/vc/modules/freevc/speaker_encoder/speaker_encoder.py
View File

@ -8,7 +8,15 @@ from torch import nn
from TTS.utils.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 import audio
from TTS.vc.modules.freevc.speaker_encoder.hparams import * from TTS.vc.modules.freevc.speaker_encoder.hparams import (
mel_n_channels,
mel_window_step,
model_embedding_size,
model_hidden_size,
model_num_layers,
partials_n_frames,
sampling_rate,
)
class SpeakerEncoder(nn.Module): class SpeakerEncoder(nn.Module):

2
recipes/bel-alex73/train_hifigan.py
View File

@ -5,7 +5,7 @@ from trainer import Trainer, TrainerArgs
from TTS.tts.configs.shared_configs import BaseAudioConfig from TTS.tts.configs.shared_configs import BaseAudioConfig
from TTS.utils.audio import AudioProcessor from TTS.utils.audio import AudioProcessor
from TTS.vocoder.configs.hifigan_config import * from TTS.vocoder.configs.hifigan_config import HifiganConfig
from TTS.vocoder.datasets.preprocess import load_wav_data from TTS.vocoder.datasets.preprocess import load_wav_data
from TTS.vocoder.models.gan import GAN from TTS.vocoder.models.gan import GAN

3
tests/data_tests/test_loader.py
View File

@ -6,9 +6,10 @@ import numpy as np
import torch import torch
from torch.utils.data import DataLoader from torch.utils.data import DataLoader
from TTS.tts.datasets.dataset import TTSDataset
from tests import get_tests_data_path, get_tests_output_path from tests import get_tests_data_path, get_tests_output_path
from TTS.tts.configs.shared_configs import BaseDatasetConfig, BaseTTSConfig from TTS.tts.configs.shared_configs import BaseDatasetConfig, BaseTTSConfig
from TTS.tts.datasets import TTSDataset, load_tts_samples from TTS.tts.datasets import load_tts_samples
from TTS.tts.utils.text.tokenizer import TTSTokenizer from TTS.tts.utils.text.tokenizer import TTSTokenizer
from TTS.utils.audio import AudioProcessor from TTS.utils.audio import AudioProcessor