Official implementation of AnimateDiff.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Machine Learning Engineering Open Book

Turn expensive prompts into cheap fine-tuned models

An unofficial PyTorch implementation of the audio LM VALL-E

LLM papers I'm reading, mostly on inference and model compression

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

A concise but complete full-attention transformer with a set of promising experimental features from various papers

Implementation of Spear-TTS - multi-speaker text-to-speech attention network, in Pytorch

Build AI Agents, Visually

Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong Audio Event Taggers"

Code, Dataset, and Pretrained Models for Audio and Speech Large Language Model "Listen, Think, and Understand".

WhisperTalk is an audio-to-text model based on the transformer architecture which takes audio input and generates predictions for the next utterance.

Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)

SoftVC VITS Singing Voice Conversion

Easily train a good VC model with voice data <= 10 mins!

🔊 Text-prompted Generative Audio Model - With the ability to clone voices

The code for the bark-voicecloning model. Training and inference.

문맥을 고려한 한국어 텍스트 데이터 증강

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 20+ clouds, or on-prem).

Code for "Learning to summarize from human feedback"

PyTorch deep learning projects made easy.

Running large language models on a single GPU for throughput-oriented scenarios.

LAVIS - A One-stop Library for Language-Vision Intelligence

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

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

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

A modular RL library to fine-tune language models to human preferences