A programmable Mixture-of-Models router for heterogeneous LLM inference

Synthetic Dialog Generation and Analysis with LLMs

Radiation Oncology NLP Database

From a+b to sparsemax(QK^T)V in Triton!

Complete solutions to the Programming Massively Parallel Processors Edition 4

Innovative approach for modelling speech disfluencies with LLaMa and Conformer.

Aligning pretrained language models with instruction data generated by themselves.

Build Anything with AI Agents

A PyTorch implementation of the 1d and 2d Sinusoidal positional encoding/embedding.

Large, modern dataset for speech recognition

Text to speech alignment using CTC forced alignment

Various speech datasets made available to the public

A framework for few-shot evaluation of language models.

This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.

Simple implementations of attention modules adapted for the biological data domain.

(unofficial) Googletrans: Free and Unlimited Google translate API for Python. Translates totally free of charge.

The BlazeFace face detector model implemented in PyTorch

Fast and accurate face landmark detection library using PyTorch; Support 68-point semi-frontal and 39-point profile landmark detection; Support both coordinate-based and heatmap-based inference; Up…

The world's simplest facial recognition api for Python and the command line

LSTM Classification using Pytorch

Yet Another Neural Machine Translation Toolkit

Interpreting BERT with LIME and SHAP

Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.

BertViz: Visualize Attention in Transformer Models

Kaldi style neural network training in pytorch for use in place of nnet3 in Kaldi.

Faster Whisper transcription with CTranslate2

Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101

Video classification tools using 3D ResNet