Implementation for "SoundCLR: Contrastive Learning of Representations For Improved Environmental Sound Classification," in pytorch.

A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models (ICASSP 2024)

MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations. A novel algorithm capable of effectively learning both augmentation invariant and equivariant features.

[ICME 2023] Semi-Supervised Federated Learing for Keyword Spotting

The code for "Efficient-PrototypicalNet with self knowledge distillation for few-shot learning"

This is the code and data for our EACL 2023 paper "The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification

Contrastive Language-Audio Pretraining

FedAudio: A Federated Learning Benchmark for Audio and Speech Tasks

✨ Open-source tool for data-centric NLP. Argilla helps domain experts and data teams to build better NLP datasets in less time.

Model for recasing and repunctuating ASR transcripts

Dataset and baseline code for the VocalSound dataset (ICASSP2022).

A new comprehensive and diverse few-shot acoustic classification benchmark.

State-of-the-art NLP tools for Turkish

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

A model that predicts the punctuation of English, Italian, French and German texts.

Official implementation of the Keyword Transformer: https://arxiv.org/abs/2104.00769

Official repository of https://arxiv.org/abs/2111.04040v1

Few-shot Keyword Spotting in Any Language and Multilingual Spoken Word Corpus

Self-Supervised Speech Pre-training and Representation Learning Toolkit.

NeMo: a toolkit for conversational AI

Official PyTorch Implementation of SSMix (Findings of ACL 2021)

A PyTorch-based Speech Toolkit

Code Repository for Liquid Time-Constant Networks (LTCs)

🧠 Minimal implementations of neural network architectures and layers in PyTorch with side-by-side notes