A practical on-device BertVITS2 runtime for Android, powered by alibaba-MNN engine. 面向移动端离线语音合成的轻量化 BertVITS2 工程实现，基于阿里 MNN 推理框架。
GitHub repository with 145 stars and 16 forks.
Language: C++
Topics: bert, bert-vits2, cppjieba, mnn, tokenizer, vits, tts, tts-android, tts-engines, android
2026-06-13: 145 stars and 16 forks.
LLM inference in C/C++
GitHub repository with 116,581 stars and 19,587 forks.
Trending score: 4.92; stars gained: +285; forks gained: +59.
Language: C++
Topics: ggml
Open Source Computer Vision Library
GitHub repository with 89,152 stars and 56,658 forks.
Trending score: 4.35; stars gained: +147; forks gained: +16.
Language: C++
Topics: c-plus-plus, computer-vision, deep-learning, image-processing, opencv
A lightweight, lightning-fast, in-process vector database
GitHub repository with 10,064 stars and 583 forks.
Trending score: 4.23; stars gained: +283; forks gained: +17.
Language: C++
Topics: agent-skills, db, embedded, faiss, hnsw, llm-memory
Port of OpenAI's Whisper model in C/C++
GitHub repository with 50,727 stars and 5,661 forks.
Trending score: 3.92; stars gained: +155; forks gained: +26.
Language: C++
Topics: inference, openai, speech-recognition, speech-to-text, transformer, whisper
A sleek and minimal desktop shell thoughtfully crafted for Wayland.
GitHub repository with 7,746 stars and 545 forks.
Trending score: 3.82; stars gained: +91; forks gained: +10.
Language: C++
Topics: dotfiles, hyprland, linux, niri, noctalia, quickshell
MLX: An array framework for Apple silicon
GitHub repository with 26,999 stars and 1,905 forks.
Trending score: 3.68; stars gained: +58; forks gained: +10.
Language: C++
open-source healthcare ai
GitHub repository with 3,484 stars and 346 forks.
Trending score: 4.93; stars gained: +302; forks gained: +41.
Language: Python
Topics: bert, deepseek, healthcare, ios, llm, mlx
This is a text classification project based on the "Category News" feature of Toutiao. Initially, we used the random forest algorithm, then upgraded to FastText, and finally built a new text classification model using a BERT pre-trained model with an added fully connected layer.There may still contain several bugs—let's work together to fix them.
GitHub repository with 101 stars and 4 forks.
Trending score: 0.96; stars gained: +0; forks gained: +0.
Language: Python
Topics: ai, bert, distilbert, fasttext-python, python, random-forest-classifier
Lightweight text embedding inference via ggml in pure C++: XLM-R/Qwen3/Gemma/MPNet/etc
GitHub repository with 18 stars and 3 forks.
Trending score: 0.57; stars gained: +0; forks gained: +1.
Language: Makefile
Topics: bert, embeddings, ggml, mpnet, xlm-roberta
Neural Network Compression Framework for enhanced OpenVINO™ inference
GitHub repository with 1,173 stars and 295 forks.
Trending score: 0.50; stars gained: +0; forks gained: +0.
Language: Python
Topics: quantization, pruning, sparsity, quantization-aware-training, mixed-precision-training, compression
json2vec turns nested, ragged data into neural representations. It lets users define typed schemas: numbers, categories, sets, dates, entities, text, etc., then trains models for prediction and embeddings. The library supports MLM-based pretraining workflows, mutations, and serving. It is built for data that does not fit cleanly into flat tables.
GitHub repository with 12 stars and 2 forks.
Trending score: 0.41; stars gained: +0; forks gained: +0.
Language: Python
Topics: bert, embeddings, feature-engineering, fraud-detection, machine-learning, nested
「从零学AI指南手册」内容自写作之初就完全是为初学者、跨学科人员所量身打造，包括机器学习、深度学习、大模型原理及RAG、Agent 开发等内容，让你轻松入门人工智能！
GitHub repository with 6 stars and 0 forks.
Trending score: 0.09; stars gained: +0; forks gained: +0.
Language: JavaScript
Topics: agent, ai, deeplearning, llm, machine-learning, rag