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
47,133 repositories indexed
1–14 of 14 · Most stars
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
A scikit-learn compatible neural network library that wraps PyTorch
Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
Feature engineering and selection open-source Python library compatible with sklearn.
Clean PyTorch implementations of imitation and reward learning algorithms
The world's cleanest AutoML library ✨ - Do hyperparameter tuning with the right pipeline abstractions to write clean deep learning production pipelines. Let your pipeline steps have hyperparameter spaces. Design steps in your pipeline like components. Compatible with Scikit-Learn, TensorFlow, and most other libraries, frameworks and MLOps environments.
A scikit-learn-compatible Python implementation of ReBATE, a suite of Relief-based feature selection algorithms for Machine Learning.
A set of tools for creating and testing machine learning features, with a scikit-learn compatible API
Seamless long-form MiniMax H3 video generation for ComfyUI with native AV latent continuity, chunked sampling, session resume, and Spectrum/Sage/Sol compatibility.
TranslatedBring the Codex imagegen workflow and prompt library to any agent; supports one-command installation with npm/pnpm, a companion skill, a standalone API, and a Qwen-Image compatible gateway.
On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese, English, Japanese and Korean.
Modular, fast NLP framework, compatible with Pytorch and spaCy, offering tailored support for French clinical notes.
Cumo (pronounced like "koomo") is CUDA aware numerical library whose interface is highly compatible with Ruby Numo