coqui-ai
/
TTS
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update the VITS model docs

pull/1032/head
Edresson 2021-09-19 13:29:09 -03:00 committed by Eren Gölge
parent cd7639ca70
commit 56480360cf
1 changed files with 8 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
TTS/tts/models/vits.py
View File

@ -159,16 +159,18 @@ class VitsArgs(Coqpit):
num_languages (int): num_languages (int):
Number of languages for the language embedding layer. Defaults to 0. Number of languages for the language embedding layer. Defaults to 0.
use_speaker_encoder_as_loss (bool): use_speaker_encoder_as_loss (bool):
Enable/Disable Speaker Consistency Loss (SCL). Defaults to False.
use_speaker_encoder_as_loss: bool = False speaker_encoder_config_path (str):
speaker_encoder_config_path: str = "" Path to the file speaker encoder config file, to use for SCL. Defaults to "".
speaker_encoder_model_path: str = ""
speaker_encoder_model_path (str):
Path to the file speaker encoder checkpoint file, to use for SCL. Defaults to "".
fine_tuning_mode (int): fine_tuning_mode (int):
Fine tuning only the vocoder part of the model, while the rest will be frozen. Defaults to 0. Fine tuning only the vocoder part of the model, while the rest will be frozen. Defaults to 0.
Mode 0: disabled; Mode 0: Disabled;
Mode 1: uses the distribution predicted by the encoder and It's recommended for TTS; Mode 1: uses the distribution predicted by the encoder and It's recommended for TTS;
Mode 2: uses the distribution predicted by the encoder and It's recommended for voice conversion. Mode 2: uses the distribution predicted by the encoder and It's recommended for voice conversion.
""" """