This repository contains the code for paper Prompting ELECTRA Few-Shot Learning with Discriminative Pre-Trained Models.

Hopular: Modern Hopfield Networks for Tabular Data

This project shows how to serve an ONNX-optimized image classification model as a web service with FastAPI, Docker, and Kubernetes.

An opensource music processing toolkit

Find and fix bugs in natural language machine learning models using adaptive testing.

chinese speech pretrained models

Repository containing experimentation platform on how to train, infer on wav2vec2 models.

Query-focused summarization data

Simple Annotated implementation of GPT-NeoX in PyTorch

Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.

Multilingual G2P in over 100 languages

Repo for ExVo 2022 Challenge

Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"

Hume AI ML Competitions

NVIDIA Riva runnable tutorials

ACL 2022: BRIO: Bringing Order to Abstractive Summarization

Sequence Modeling with Structured State Spaces

Evaluation and Benchmarking of Speech Super-resolution Methods

Voice models for Mimic 3 text to speech system

An implementation of Microsoft's "AdaSpeech: Adaptive Text to Speech for Custom Voice"

A Non-Autoregressive End-to-End Text-to-Speech, supporting a family of SOTA unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate E2E-TTS

Text analysis with networks.

Official code for Wav2Seq

End-to-end MOdeling of ASR (Automatic Speech Recognition)