Hugging Face's logo
Zixi "Oz" Li's picture
🏗️ Building on HF

Zixi "Oz" Li

OzTianlu
9 32 46
kkish's profile picture skvin's profile picture warfazeee's profile picture
·
https://github.com/lizixi-0x2F

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 👀 3 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 3 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 3 days ago
NoesisLab/zixi-51m
View all activity

Organizations

LocalLLaMA's profile picture Hugging Face Discord Community's profile picture NoesisLab's profile picture Unsloth Jobs Explorers's profile picture Reasoning Kingdom's profile picture