metadata
license: cc-by-nc-4.0
datasets:
- OOPPEENN/56697375616C4E6F76656C5F44617461736574
- amphion/Emilia-Dataset
- litagin/ehehe-corpus
- joujiboi/japanese-anime-speech
- OmniAICreator/ASMR-Archive-Processed
language:
- ja
base_model:
- HKUSTAudio/Llasa-3B
pipeline_tag: text-to-speech
Anime-Llasa-3B
Overview
This is the Anime-Llasa-3B, a Text-to-Speech (TTS) model fine-tuned for Japanese. This model is based on HKUSTAudio/Llasa-3B.
Demo
You can try a demo on Hugging Face Spaces: Anime-Llasa-3B-Demo
What's New?
The primary improvement in this version is a significant increase in the training data. The amount of training data has been increased from approximately 14,000 hours (3 epochs) to approximately 33,000 hours (1 epoch).
This enhancement aims to further improve the model's expressiveness and overall stability.
Old Version
License
This model is licensed under the CC-BY-NC-4.0.