Repository Index

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

• audio
• deeplearning
• minicpm
• python

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

• calibration
• classification
• decision-model
• huggingface

See, hear, and interact on your local devices.

• minicpm
• minicpm-v
• multi-modal
• minicpm-o

A multi-voice TTS system trained with an emphasis on quality

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Depth-Aware Video Frame Interpolation (CVPR 2019)

Open source AI clip generator: turns long videos into viral 9:16 shorts with AI moment detection, face tracking, subtitles and dubbing. Self-host free with Docker (MIT), or use the cloud with GPU speed from $12/mo. MCP server and API for AI agents.

• clip-generator
• open-source
• shorts
• tiktok

:fire: 2D and 3D Face alignment library build using pytorch

• python
• deep-learning
• face-alignment
• face-detector

Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

• apple-silicon
• inference
• machine-learning
• mlx

Scalable and user friendly neural :brain: forecasting algorithms.

• deep-learning
• forecasting
• esrnn
• nbeats

Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 48kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt

• deep-learning
• text-to-speech
• on-device-ml
• real-time

Fast, accurate OCR with correctness assessment.

• image2text
• minicpm-v
• ocr

Ensembles of decision trees in go/golang.

LiDAR point cloud ground filtering / segmentation (bare earth extraction) method based on cloth simulation

Translated斑海豹 (Spotted Seal) — Phocinae-Largha-150M-v1: a 144.3M bilingual decision model. Tiny model. Big decisions.

• bilingual
• calibration
• cpu-inference
• decision-making

[IROS 2020] se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains

• robotics
• tracking
• computer-vision
• pose-estimation

Continuous area cartograms with d3 and TopoJSON

• cartogram
• javascript
• topojson
• topology

The repository host gives no description.

TavernGym and TavernBench: a faithful, full-content Hearthstone Battlegrounds simulator with an RL interface, and a 960-task decision benchmark. Code and data for "Build, Don't Play".

• game-ai
• hearthstone
• reinforcement-learning
• rust

The official code of FrameMorrow: Future-Guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation.

OpenBioLink is a resource and evaluation framework for evaluating link prediction models on heterogeneous biomedical graph data.

A robust, full-featured Ruby implementation of Naive Bayes

Interpretable bilinear attention network with domain adaptation improves drug-target prediction.

The repository host gives no description.

• model-interpretation