Repository Index

Easily train a good VC model with voice data <= 10 mins!

• change
• sovits
• vits
• voice

MLX: An array framework for Apple silicon

• mlx

Stable Diffusion with Core ML on Apple Silicon

A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

• apple-silicon
• audio-processing
• mlx
• multimodal

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

• bert
• transformers
• topic-modeling
• sentence-embeddings

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

On-device Speech AI for Apple Silicon

• inference
• ios
• speech-recognition
• swift

Silero Models: pre-trained text-to-speech models made embarrassingly simple

• speech-to-text
• pretrained-models
• pytorch
• colab

Dockerized OpenAI-compatible wrapper for Kokoro-82M text-to-speech w/multiplatform CPU, AMD, NVIDIA GPU PyTorch; multi-speaker, clone-tuning, caption timestamps, SSML, websockets, optional readalong web UI

• fastapi
• tts
• tts-api
• kokoro

Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.

• keras
• deep-learning
• text-generation
• tensorflow

An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.

• ai
• amd-gpu
• apple-silicon
• asr

Todas as leis do Brasil

Local speech-to-text for macOS on-device AI, fully private, optional cloud

• apple-silicon
• dictation
• macos
• on-device

Easily craft fast Neural Networks on iOS! Use TensorFlow models. Metal under the hood.

• machine-learning
• neural-networks
• metal
• apple

java deep learning algorithms and deep neural networks with gpu acceleration

🐋 Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs). SwiGLU-H2, Stockfish-PVS L3 & 13ms Claude Code restore.

• avx512
• cpu-inference
• hpc
• llama-cpp

Imagination Studio by keys+Wasserman powered by TensorFold: an AI film studio for Mac and NVIDIA DGX Spark. Plan a film like a crew (Slate workflow by Sam Wasserman), render Qwen-Image-2.1 / FLUX3-K pictures and MiniMax H3 / FastH3 video with sound on TensorFold.

• apple-silicon
• minimax-h3
• mlx
• qwen-image

C++ implementation of a fast and memory efficient HAT-trie

• cpp
• trie
• hat-trie
• data-structures

Corpus legislativo brasileiro em larga escala e modelo Transformer causal treinado do zero em PyTorch puro.

Highly interpretable classifiers for scikit learn, producing easily understood decision rules instead of black box models

Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR, ReazonSpeech, parakeet and Silero VAD on Metal, Vulkan and the CPU, with an OpenAI-compatible server and live transcription.

• cpp
• ggml
• gguf
• metal

Free desktop app that turns a text prompt into a short video clip on your own PC. Local AI text-to-video with Wan 2.2: type a scene, pick wide, vertical or square, get an MP4. No credits, no subscription, no queue. Windows 10/11.

• ai-tools
• ai-video
• ai-video-clip
• ai-video-generator-crack

High-performance Piecewise Geometric Model (PGM) learned index implementation in pure Rust with strict epsilon error guarantees

Multilingual library to easily parse date strings to java.util.Date objects.

• clojure
• parsing
• date-time
• date-parser