开发者用近100小时土耳其语数据微调 VoxCPM2

OpenBMB · @OpenBMB · X·2026-09-17 21:00·3小时前
AI 导读

开发者 @AlicanKiraz0 基于 VoxCPM2 微调出 Kahya-TTS,用近 100 小时自然土耳其语语音数据,将其语音生成能力适配到土耳其语 TTS。该模型已在 Hugging Face 开源,用于探索开源语音模型向新语言和专用数据集的适配。

OpenBMB@OpenBMB
27AI 编辑部评分,满分 100

开发者用近100小时土耳其语数据微调 VoxCPM2

2026-09-17 21:00· 3小时前
AI 导读

开发者 @AlicanKiraz0 基于 VoxCPM2 微调出 Kahya-TTS,用近 100 小时自然土耳其语语音数据,将其语音生成能力适配到土耳其语 TTS。该模型已在 Hugging Face 开源,用于探索开源语音模型向新语言和专用数据集的适配。

🎙️ VoxCPM2 meets Turkish voice data!

Developer @AlicanKiraz0 fine-tuned VoxCPM2 with nearly 100 hours of natural Turkish speech data, adapting its voice generation capabilities specifically for Turkish text-to-speech.

With VoxCPM2 as the foundation, Kahya-TTS explores how open-source voice models can be further adapted to new languages and specialized datasets.

✨ Highlights: 🇹🇷 Turkish TTS powered by VoxCPM2 🎙️ Nearly 100 hours of natural Turkish voice data ⚡ Fine-tuning tailored to Turkish speech synthesis 🛠️ Open-source model adaptation for further research and development

Great example of what developers can build on top of VoxCPM2. 🙌

🔗 Model: http://huggingface.co/AlicanKiraz0/Kahya-TTS-v1.0 🤗 VoxCPM2: http://huggingface.co/openbmb/VoxCPM2

Building with VoxCPM2? We’d love to see what you create. 🙌

来源:OpenBMB· x.com