wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-09 11:16:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Mass refactoring

Browse Source
This commit is contained in:
erogol
2020-07-17 11:16:05 +02:00
parent 3bc38517aa
commit 82dd465365
148 changed files with 3698 additions and 13887 deletions
Download Patch File Download Diff File Expand all files Collapse all files
notebooks/ExtractTTSpectrogram.ipynb
+7 -7
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.datasets.TTSDataset import MyDataset\n",
"from TTS.layers.losses import L1LossMasked\n",
"from TTS.utils.audio import AudioProcessor\n",
"from TTS.utils.visual import plot_spectrogram\n",
"from TTS.utils.generic_utils import load_config, setup_model, sequence_mask\n",
"from 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('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",