Model Details
Model Type: Text-to-Speech (TTS)
Architecture: Bert-Vits2
Training Data: Custom dataset derived from publicly available audio clips of Prof. Luo Xiang, a renowned Chinese legal scholar.
Language: Chinese (Mandarin)
This model is a BERT-VITS2-based TTS voice synthesis system trained on audio samples from Luo Xiang, a prominent public legal scholar, to mimic his Mandarin speech patterns. It is intended solely for personal learning and non-commercial purposes. If any copyright infringement is identified, please contact the author immediately for resolution.
- Downloads last month
- 7
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for bladedragon/luoxiang_bert_vit2
Base model
hfl/chinese-roberta-wwm-ext