Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Official release of InternLM2.5 base and chat models. 1M context support

🔊 Text-Prompted Generative Audio Model

SoftVC VITS Singing Voice Conversion

vits2 backbone with multilingual-bert

Hydra is a framework for elegantly configuring complex applications

Tracking the progress in end-to-end speech translation

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models

Foundational Models for State-of-the-Art Speech and Text Translation

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

搜集、整理、发布 中文 自然语言处理 语料/数据集，与 有志之士 共同 促进 中文 自然语言处理 的 发展。

Pushing the Limits of Zero-shot End-to-End Speech Translation

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

Mirror of https://git.ffmpeg.org/ffmpeg.git

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

TransferTTS (Zero-Shot learning of VITS)

chinese speech pretrained models

手把手带你实战 Huggingface Transformers 课程视频同步更新在B站与YouTube

This is an implementation of paper "End-to-end Speech Translation via Cross-modal Progressive Training" (Interspeech2021)

A fast speech-to-speech & speech-to-text translation model that supports simultaneous decoding and offers 28× speedup.

Code for ACL 2022 main conference paper "STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation".

code for paper "Cross-modal Contrastive Learning for Speech Translation" (NAACL 2022)

Fast and memory-efficient exact attention

dataset for lightly supervised training using the librivox audio book recordings. https://librivox.org/.

This repository contains demos I made with the Transformers library by HuggingFace.

Notebooks using the Hugging Face libraries 🤗

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image