diff --git a/recipes/vctk/yourtts/train_yourtts.py b/recipes/vctk/yourtts/train_yourtts.py index 1487a9fc..aa584396 100644 --- a/recipes/vctk/yourtts/train_yourtts.py +++ b/recipes/vctk/yourtts/train_yourtts.py @@ -8,7 +8,7 @@ from TTS.bin.resample import resample_files from TTS.config.shared_configs import BaseDatasetConfig from TTS.tts.configs.vits_config import VitsConfig from TTS.tts.datasets import load_tts_samples -from TTS.tts.models.vits import Vits, VitsArgs, VitsAudioConfig +from TTS.tts.models.vits import CharactersConfig, Vits, VitsArgs, VitsAudioConfig from TTS.utils.downloaders import download_vctk torch.set_num_threads(24) @@ -151,7 +151,19 @@ config = VitsConfig( phoneme_language="en", compute_input_seq_cache=True, add_blank=True, - text_cleaner="english_cleaners", + text_cleaner="multilingual_cleaners", + characters=CharactersConfig( + characters_class="TTS.tts.models.vits.VitsCharacters", + pad="_", + eos="&", + bos="*", + blank=None, + characters="ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\u00af\u00b7\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u00f9\u00fa\u00fb\u00fc\u00ff\u0101\u0105\u0107\u0113\u0119\u011b\u012b\u0131\u0142\u0144\u014d\u0151\u0153\u015b\u016b\u0171\u017a\u017c\u01ce\u01d0\u01d2\u01d4\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044a\u044b\u044c\u044d\u044e\u044f\u0451\u0454\u0456\u0457\u0491\u2013!'(),-.:;? ", + punctuations="!'(),-.:;? ", + phonemes="", + is_unique=True, + is_sorted=True, + ), phoneme_cache_path=None, precompute_num_workers=12, start_by_longest=True,