From b3ed6ff6b74947dbcaaa41fae5060e18b84cc27d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eren=20G=C3=B6lge?= Date: Tue, 25 Jan 2022 09:29:21 +0000 Subject: [PATCH] Update FastPitchConfig --- TTS/tts/configs/fast_pitch_config.py | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/TTS/tts/configs/fast_pitch_config.py b/TTS/tts/configs/fast_pitch_config.py index 8f063102..de870388 100644 --- a/TTS/tts/configs/fast_pitch_config.py +++ b/TTS/tts/configs/fast_pitch_config.py @@ -89,12 +89,9 @@ class FastPitchConfig(BaseTTSConfig): pitch_loss_alpha (float): Weight for the pitch predictor's loss. If set 0, disables the pitch predictor. Defaults to 1.0. - binary_loss_alpha (float): + binary_align_loss_alpha (float): Weight for the binary loss. If set 0, disables the binary loss. Defaults to 1.0. - binary_align_loss_start_step (int): - Start binary alignment loss after this many steps. Defaults to 20000. - min_seq_len (int): Minimum input sequence length to be used at training. @@ -129,12 +126,12 @@ class FastPitchConfig(BaseTTSConfig): duration_loss_type: str = "mse" use_ssim_loss: bool = True ssim_loss_alpha: float = 1.0 - dur_loss_alpha: float = 1.0 spec_loss_alpha: float = 1.0 - pitch_loss_alpha: float = 1.0 aligner_loss_alpha: float = 1.0 - binary_align_loss_alpha: float = 1.0 - binary_align_loss_start_step: int = 20000 + pitch_loss_alpha: float = 0.1 + dur_loss_alpha: float = 0.1 + binary_align_loss_alpha: float = 0.1 + binary_loss_warmup_epochs: int = 150 # overrides min_seq_len: int = 13