🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Robust Speech Recognition via Large-Scale Weak Supervision

Deezer source separation library including pretrained models.

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

Go ahead and axolotl questions

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

fast-stable-diffusion + DreamBooth

PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The most effective open source solution to turn your pdf files in a chatbot!

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

A treasure chest for visual classification and recognition powered by PaddlePaddle

PyTorch native post-training library

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Let ChatGPT teach your own chatbot in hours with a single GPU!

An unofficial PyTorch implementation of the audio LM VALL-E

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

Core Engine of Singing Voice Conversion & Singing Voice Clone

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

Scrape Twitter for Tweets

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

Scalable data pre processing and curation toolkit for LLMs

A family of lightweight multimodal models.

An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.

Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection

All-in-one text de-duplication

Grounded search engine (i.e. with source reference) based on LLM / ChatGPT / OpenAI API. It supports web search, file content search etc.

Original Implementation of Prompt Tuning from Lester, et al, 2021

This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on