From b73b4452785e165abb6bb1a701239f086e89252c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eren=20G=C3=B6lge?= Date: Tue, 3 May 2022 13:44:32 +0200 Subject: [PATCH] Update VITS VCTK recipe --- recipes/vctk/vits/train_vits.py | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-) diff --git a/recipes/vctk/vits/train_vits.py b/recipes/vctk/vits/train_vits.py index 88fd7de9..1bd88509 100644 --- a/recipes/vctk/vits/train_vits.py +++ b/recipes/vctk/vits/train_vits.py @@ -2,11 +2,10 @@ import os from trainer import Trainer, TrainerArgs -from TTS.config.shared_configs import BaseAudioConfig from TTS.tts.configs.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 +from TTS.tts.models.vits import Vits, VitsArgs, VitsAudioConfig from TTS.tts.utils.speakers import SpeakerManager from TTS.tts.utils.text.tokenizer import TTSTokenizer from TTS.utils.audio import AudioProcessor @@ -17,22 +16,13 @@ dataset_config = BaseDatasetConfig( ) -audio_config = BaseAudioConfig( +audio_config = VitsAudioConfig( sample_rate=22050, win_length=1024, hop_length=256, num_mels=80, - preemphasis=0.0, - ref_level_db=20, - log_func="np.log", - do_trim_silence=True, - trim_db=23.0, mel_fmin=0, - mel_fmax=None, - spec_gain=1.0, - signal_norm=False, - do_amp_to_db_linear=False, - resample=True, + mel_fmax=None ) vitsArgs = VitsArgs( @@ -62,6 +52,7 @@ config = VitsConfig( max_text_len=325, # change this if you have a larger VRAM than 16GB output_path=output_path, datasets=[dataset_config], + cudnn_benchmark=False ) # INITIALIZE THE AUDIO PROCESSOR