Multimodal language model benchmark, featuring challenging examples

Structured Text Generation

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

GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm

LLM training code for Databricks foundation models

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

A Data Streaming Library for Efficient Neural Network Training

Reference implementation for DPO (Direct Preference Optimization)

MeetEval - A meeting transcription evaluation toolkit

INTERSPEECH 2023 Papers: A complete collection of influential and exciting research papers from the INTERSPEECH 2023 conference. Explore the latest advances in speech and language processing. Code …

Tools for handling speech data in machine learning projects.

Easily create large video dataset from video urls

Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets

String-to-String Algorithms for Natural Language Processing

ImageBind One Embedding Space to Bind Them All

the subtitle editor :)

Simple Diarization model

Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva

Minimal extension of OpenAI's Whisper adding speaker diarization with special tokens

GPT4All: Chat with Local LLMs on Any Device

[CVPR'23 Highlight] AutoAD: Movie Description in Context.

A database of movie scripts from several sources

Inference code for Llama models

gpu tester detects broken and slow gpus in a cluster

Implementation of "Slow-Fast Auditory Streams for Audio Recognition, ICASSP, 2021" in PyTorch

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

AWS ParallelCluster is an AWS supported Open Source cluster management tool to deploy and manage HPC clusters in the AWS cloud.