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

ICLR2023 statistics

This repo includes ChatGPT prompt curation to use ChatGPT better.

Awesome papers on Language-Model-as-a-Service (LMaaS)

A curated list of awesome datasets with human label variation (un-aggregated labels) in Natural Language Processing and Computer Vision, accompanying The 'Problem' of Human Label Variation: On Grou…

Adaptive Experimentation Platform

Pytorch implementation of "Joint Acne Image Grading and Counting via Label Distribution Learning"

Torchmetrics - Machine learning metrics for distributed, scalable PyTorch applications.

[INTERSPEECH'2022] Accurate Emotion Strength Assessment for Seen and Unseen Speech Based on Data-Driven Deep Learning

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).

Long Range Arena for Benchmarking Efficient Transformers

Crowd Sourced Emotional Multimodal Actors Dataset (CREMA-D)

Comparing self-supervised model for speech emotion recognition task

the PyTorch implementation of chunk-level attention-based temporal aggregation framework for sequence-to-one recognition tasks

Semi-supervised Domain Adaptation via Minimax Entropy

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

How to use our public wav2vec2 dimensional emotion model

Code to support characterizing sources of uncertainty to proxy calibration and disambiguate annotator and data bias.

Light-SERNet: A lightweight fully convolutional neural network for speech emotion recognition

This is the official code for paper "Speech Emotion Recognition with Global-Aware Fusion on Multi-scale Feature Representation" published in ICASSP 2022

CVPR 2022, Robust Contrastive Learning against Noisy Views

A library for performing coverage guided fuzzing of neural networks

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

Evolutionary Scale Modeling (esm): Pretrained language models for proteins

Pytorch implementation of "Block Recurrent Transformers" (Hutchins & Schlag et al., 2022)

Code for the AAAI 2022 paper "SSAST: Self-Supervised Audio Spectrogram Transformer".

Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".

Code for reproducing results from our paper, Robustness of conditional GANs to noisy labels, NIPS 2018