sparse_autoencoder

vdvae

Repository for the paper "Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them...

glow

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

faster-whisper

Faster Whisper transcription with CTranslate2

neural-gpu

Code for the Neural GPU model originally described in "Neural GPUs Learn Algorithms"

transformer-debugger

CLIP

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

sparse_attention

Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"

Whisper-Finetune

Fine-tune the Whisper speech recognition model to support training without timestamp data, traini...

ebm_code_release

Code for Implicit Generation and Generalization with Energy Based Models

improved-diffusion

Release for Improved Denoising Diffusion Probabilistic Models

whisper-jax

JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.

image-gpt

automated-interpretability

blocksparse

Efficient GPU kernels for block-sparse matrix multiplication and convolution

go-whisper

Speech o Text using docker image with ggerganov/whisper.cpp