Easily train a good VC model with voice data <= 10 mins!
- change
- sovits
- vits
- voice
47,133 repositories indexed
1–14 of 14 · Most stars
Easily train a good VC model with voice data <= 10 mins!
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Topic Modelling for Humans
Unified framework for building enterprise RAG pipelines with small, specialized models
[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
Visual localization made easy with hloc
Accelerated deep learning R&D
Deep neural network to extract intelligent information from invoice documents.
Python audio and music signal processing library
allRank is a framework for training learning-to-rank neural models based on PyTorch.