Kizagan-TTS-v1.0

Turkish fine-tuning and release: Alican Kiraz.
Base model and VoxCPM implementation: OpenBMB / VoxCPM team.
Base model: https://huggingface.co/openbmb/VoxCPM2
Upstream code: https://github.com/OpenBMB/VoxCPM

The model weights include the previously merged Kızagan Step1500 LoRA adaptation.
The tokenizer/configuration/AudioVAE assets originate from VoxCPM2.
The Apache-2.0 license text is preserved in LICENSE.
The private training dataset and its source recordings are not redistributed here.