A 6-million Audio-Caption Paired Dataset Built with a LLMs and ALMs-based Automatic Pipeline

Fast and memory-efficient exact attention

This is the repository for the BioCLIP model and the TreeOfLife-10M dataset [CVPR'24 Oral, Best Student Paper].

Juptyer notebook tutorials on using the data in the AWS pacific-sound registry for ocean soundscape research, education, and the arts

BLSP: Bootstrapping Langauge-Speech Pre-training via Behavior Alignment of Continuation Writing

Contrastive language-audio pretraining for bioacoustics

AnuraSet: A dataset for classification of tropical anurans from passive acoustic monitoring

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

Text-to-Audio/Music Generation

Anthropic Claude2 Hackathon:Building MCTS with Claude for optimal action prediction during patient/doctor interactions.

The Biologger Ethogram Benchmark

Contrast-agnostic segmentation of MRI scans

Let us control diffusion models!

AudioLDM: Generate speech, sound effects, music and beyond, with text.

Audio generation using diffusion models, in PyTorch.

A benchmark dataset for data-driven weather forecasting

Reimplementing Karpathy's micrograd for fun

AVES: Animal Vocalization Encoder based on Self-Supervision

BEANS: The Benchmark of Animal Sounds

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

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

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Grounded Language-Image Pre-training

Code for ALBEF: a new vision-language pre-training method

Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch

Library for clinical NLP with spaCy.