wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-10 11:50:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

add text parameters in config.json

Browse Source
This commit is contained in:
Edresson Casanova
2020-03-01 15:47:08 -03:00
parent e7ef4e9050
commit 8feb326a60
16 changed files with 126 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files
notebooks/Benchmark-PWGAN.ipynb
+5 -1
View File
@@ -132,7 +132,7 @@
"outputs": [],
"source": [
"# LOAD TTS MODEL\n",
"from TTS.utils.text.symbols import symbols, phonemes\n",
"from TTS.utils.text.symbols import make_symbols, symbols, phonemes\n",
"\n",
"# multi speaker \n",
"if CONFIG.use_speaker_embedding:\n",
@@ -142,6 +142,10 @@
" speakers = []\n",
" speaker_id = None\n",
"\n",
"# if the vocabulary was passed, replace the default\n",
"if 'text' in CONFIG.keys():\n",
" symbols, phonemes = make_symbols(**CONFIG.text)\n",
"\n",
"# load the model\n",
"num_chars = len(phonemes) if CONFIG.use_phonemes else len(symbols)\n",
"model = setup_model(num_chars, len(speakers), CONFIG)\n",
notebooks/Benchmark.ipynb
+5 -1
View File
@@ -65,7 +65,7 @@
"from TTS.utils.text import text_to_sequence\n",
"from TTS.utils.synthesis import synthesis\n",
"from TTS.utils.visual import visualize\n",
"from TTS.utils.text.symbols import symbols, phonemes\n",
"from TTS.utils.text.symbols import make_symbols, symbols, phonemes\n",
"\n",
"import IPython\n",
"from IPython.display import Audio\n",
@@ -149,6 +149,10 @@
" speakers = []\n",
" speaker_id = None\n",
"\n",
"# if the vocabulary was passed, replace the default\n",
"if 'text' in CONFIG.keys():\n",
" symbols, phonemes = make_symbols(**CONFIG.text)\n",
"\n",
"# load the model\n",
"num_chars = len(phonemes) if CONFIG.use_phonemes else len(symbols)\n",
"model = setup_model(num_chars, len(speakers), CONFIG)\n",
notebooks/ExtractTTSpectrogram.ipynb
+6 -2
View File
@@ -37,7 +37,7 @@
"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 symbols, phonemes\n",
"from TTS.utils.text.symbols import make_symbols, symbols, phonemes\n",
"\n",
"%matplotlib inline\n",
"\n",
@@ -94,6 +94,10 @@
"metadata": {},
"outputs": [],
"source": [
"# if the vocabulary was passed, replace the default\n",
"if 'text' in C.keys():\n",
" symbols, phonemes = make_symbols(**C.text)\n",
"\n",
"# load the model\n",
"num_chars = len(phonemes) if C.use_phonemes else len(symbols)\n",
"# TODO: multiple speaker\n",
@@ -116,7 +120,7 @@
"preprocessor = importlib.import_module('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, ap, meta_data, use_phonemes=C.use_phonemes, phoneme_cache_path=C.phoneme_cache_path, enable_eos_bos=C.enable_eos_bos_chars)\n",
"dataset = MyDataset(checkpoint['r'], C.text_cleaner, ap, meta_data,tp=C.text if 'text' 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",
"loader = DataLoader(dataset, batch_size=BATCH_SIZE, num_workers=4, collate_fn=dataset.collate_fn, shuffle=False, drop_last=False)"
]
},
notebooks/TestAttention.ipynb
+5 -1
View File
@@ -100,7 +100,7 @@
"outputs": [],
"source": [
"# LOAD TTS MODEL\n",
"from TTS.utils.text.symbols import symbols, phonemes\n",
"from TTS.utils.text.symbols import make_symbols, symbols, phonemes\n",
"\n",
"# multi speaker \n",
"if CONFIG.use_speaker_embedding:\n",
@@ -110,6 +110,10 @@
" speakers = []\n",
" speaker_id = None\n",
"\n",
"# if the vocabulary was passed, replace the default\n",
"if 'text' in CONFIG.keys():\n",
" symbols, phonemes = make_symbols(**CONFIG.text)\n",
"\n",
"# load the model\n",
"num_chars = len(phonemes) if CONFIG.use_phonemes else len(symbols)\n",
"model = setup_model(num_chars, len(speakers), CONFIG)\n",