Hugging Face's logo

Akjava
/
matcha-tts_ja_100speakers_group003f-fromscratch-with-CL

TensorBoard
Japanese
Model card Files
xet
Metrics Community

Speakers 

0  - ja004_speech_common-voice_22khz

Trainings settings

Stage 1 2 3

batch 180

Stage4

batch 150

Stage5

batch 80

StageExtra1

After This Stage Valid Loss is useless

merge valid files for final learning.

StageExtra2

add mora-speaks from group3f-fromscratch. some mora/phonome is not learned yet,to boostup learn.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Akjava/matcha-tts_ja_100speakers_group003f-fromscratch-with-CL

Finetunes
1 model

Dataset used to train Akjava/matcha-tts_ja_100speakers_group003f-fromscratch-with-CL

Collection including Akjava/matcha-tts_ja_100speakers_group003f-fromscratch-with-CL