arxiv:2606.07207
🏗️ Building on HF
Zixi "Oz" Li
OzTianlu
AI & ML interests
My research focuses on deep reasoning with small language models, Transformer architecture innovation, and knowledge distillation for efficient alignment and transfer.
Recent Activity
reacted to theirpost with 👀 21 days ago
zixi-51M: Not a stock voice. A voice. 🐾
https://huggingface.co/NoesisLab/zixi-51m
Everyone is shipping 500B-parameter models. I shipped 51 million. With one voice. On purpose. 🎤
What: open-weights Chinese TTS. VITS2 lineage. 51.43M params. Runs on your laptop CPU — no cloud, no API key, no GPU bill, no meter running.💸
The voice: not a stock voice, not a 5,000-speaker average. One real human's voice — mine. Timbre, rhythm, breath included. The sample on themodel card is one take, default parameters, recorded by absolutely no one. 🎧
What's NOT inside:
• ❌ BERT (zero. the text encoder vibes on phones + tones alone)
• ❌ language routing (Chinese-exclusive: 77 symbols, 6 tones, one job)
• ❌ my training data (the corpus is my own writing and stays mine — open weights, closed corpus, that's the deal 🤝)
The trick: embedding transplant. Phone, tone and speaker rows inherited from the MeloTTS-Chinese base by symbol name — no random init. Themodel woke up already knowing Chinese. 🧠
Built solo, corpus to packaging, by a writer who is also a violinist. Prosody is my day job. 🎻
Use it, fork it, fine-tune your own voice. Just don't put words in a real person's mouth. 🙏
🔗 Weights: https://huggingface.co/NoesisLab/zixi-51m
💻 Code: https://github.com/lizixi-0x2F/zixi-51M posted an update 21 days ago
zixi-51M: Not a stock voice. A voice. 🐾
https://huggingface.co/NoesisLab/zixi-51m
Everyone is shipping 500B-parameter models. I shipped 51 million. With one voice. On purpose. 🎤
What: open-weights Chinese TTS. VITS2 lineage. 51.43M params. Runs on your laptop CPU — no cloud, no API key, no GPU bill, no meter running.💸
The voice: not a stock voice, not a 5,000-speaker average. One real human's voice — mine. Timbre, rhythm, breath included. The sample on themodel card is one take, default parameters, recorded by absolutely no one. 🎧
What's NOT inside:
• ❌ BERT (zero. the text encoder vibes on phones + tones alone)
• ❌ language routing (Chinese-exclusive: 77 symbols, 6 tones, one job)
• ❌ my training data (the corpus is my own writing and stays mine — open weights, closed corpus, that's the deal 🤝)
The trick: embedding transplant. Phone, tone and speaker rows inherited from the MeloTTS-Chinese base by symbol name — no random init. Themodel woke up already knowing Chinese. 🧠
Built solo, corpus to packaging, by a writer who is also a violinist. Prosody is my day job. 🎻
Use it, fork it, fine-tune your own voice. Just don't put words in a real person's mouth. 🙏
🔗 Weights: https://huggingface.co/NoesisLab/zixi-51m
💻 Code: https://github.com/lizixi-0x2F/zixi-51M updated a model 21 days ago
NoesisLab/zixi-51mOrganizations
