初始化项目,由ModelHub XC社区提供模型
Model: MrDragonFox/baddy_S3_EXP_3 Source: Original Platform
This commit is contained in:
22
README.md
Normal file
22
README.md
Normal file
@@ -0,0 +1,22 @@
|
||||
---
|
||||
license: cc-by-nc-4.0
|
||||
tags:
|
||||
- unsloth
|
||||
---
|
||||
(m)orpheus t(i)t(t)s
|
||||
- Uncensored Orpheus tts
|
||||
|
||||
finetune of orpheus on uncensored/ (un)alingned data to be able to generate more interresting sounds
|
||||
|
||||
SEASION3 - Experiment 3
|
||||
|
||||
speaker name is "baddy" - trained on base
|
||||
prob. final checkpoint for the time beeing
|
||||
|
||||
seems to even work with voice cloneing fine if you keep the speaker as baddy
|
||||
|
||||
bug reports / recommendations please in the discord https://discord.gg/RUs3uzBdW3
|
||||
|
||||
training still under way
|
||||
|
||||
does less tags but generalise rather well
|
||||
Reference in New Issue
Block a user