AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Command-line program to download videos from YouTube.com and other video sites

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Robust Speech Recognition via Large-Scale Weak Supervision

Inference code for Llama models

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

结巴中文分词

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

A generative speech model for daily dialogue.

A high-throughput and memory-efficient inference and serving engine for LLMs

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Hydra is a framework for elegantly configuring complex applications

vits2 backbone with multilingual-bert

ModelScope: bring the notion of Model-as-a-Service to life.

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

用文本编辑器剪视频

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Modeling, training, eval, and inference code for OLMo

中文自然语言处理数据集，平时做做实验的材料。欢迎补充提交合并。

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Production First and Production Ready End-to-End Speech Recognition Toolkit

On-device wake word detection powered by deep learning

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

Multilingual Voice Understanding Model

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.