Repository Index

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

• deep-learning
• pytorch
• gpu
• machine-learning

Making large AI models cheaper, faster and more accessible

• deep-learning
• hpc
• large-scale
• data-parallelism

Privacy-first AI meeting note taker for Windows and macOS. Free, open source (MIT). On-device Whisper/Parakeet transcription and speaker diarization, no meeting bot. Open-source alternative to Granola, Otter and Fireflies. https://meetily.ai

• meeting-minutes
• meeting-notes
• llm
• mac

GUI for a Vocal Remover that uses Deep Neural Networks.

• vocal-remover
• pytorch
• source
• separation

TranslatedPArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice (Core framework of 'PaddlePaddle' (飞桨, Feijiang), for deep learning & machine learning: high-performance single-machine and distributed training, and cross-platform deployment)

• paddlepaddle
• deep-learning
• scalability
• machine-learning

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

• pytorch
• speech-recognition
• paraformer
• punctuation

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

• gbdt
• gbm
• machine-learning
• data-mining

Ongoing research training transformer models at scale

• large-language-models
• model-para
• transformers

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).

• llm
• lora
• sft
• multimodal

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

• asr
• onnx
• windows
• linux

A hyperparameter optimization framework

• python
• machine-learning
• parallel
• distributed

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

• attention-mechanism
• deep-learning
• gpt
• gpt-2

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

• attention
• pytorch
• paper
• cbam

A PyTorch-based Speech Toolkit

• speech-recognition
• speech-toolkit
• speaker-recognition
• speech-to-text

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

• machine-learning
• experiment-track
• deep-learning
• keras

Fast and Accurate ML in 3 Lines of Code

• automl
• machine-learning
• data-science
• deep-learning

A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.

• machine-learning
• python
• data-science
• automl

Automated Machine Learning with scikit-learn

• automl
• scikit-learn
• automated-machine-learning
• hyperparameter-optimization

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

• speech-synthesis
• text-to-speech
• tensorflow2
• melgan

AI Infra / AI Orchestration / AI Control Plane

• deep-learning
• machine-learning
• artificial-intelligence
• data-science

Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

• coreml
• ios
• macos
• speaker-diarization

Determined is an open-source machine learning platform that simplifies distributed training, hyperparameter tuning, experiment tracking, and resource management. Works with PyTorch and TensorFlow.

• deep-learning
• machine-learning
• ml-platform
• ml-infrastructure

macOS dictation app

• macos
• whisper
• parakeet
• dictation

Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.

• controllable-generation
• foundation-models
• image-generation
• text-rendering