oplatek

moosenet-plda

Official repo for “MooseNet: A Trainable Metric for Synthesized Speech with a PLDA Module”

chateval-llm

Three Ways of Using Large Language Models to Evaluate Chat. A system description of Dstc11 Track 4 submission.

dotfiles-vim

shellgit-ufal

speechwoz

ToD-BERT

Pre-Trained Models for ToD-BERT

alignment-handbook

Robust recipes for to align language models with human and AI preferences

cgw

Competitive Grammar Writing in Python

COMET

A Neural Framework for MT Evaluation

DCASE2019_task4

Baseline of dcase 2019 task 4

doccano

Open source annotation tool for machine learning practitioners.

DSTC11-Benchmark

factgenie-table-to-text

JSALT2023-MT-lab

lhotse

lightning-kitti

Semantic Segmentation with Pytorch-Lightning

lstm-parser

Transition-based dependency parser based on stack LSTMs

mbrs

A library for minimum Bayes risk (MBR) decoding

MT-Marathon-Tutorial-2024

Tutorial about using LLMs for translation and performing MBR on top

oplatek.github.io

plda

Probabilistic Linear Discriminant Analysis & classification, written in Python.

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

quintd

Code for the paper Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation

reffix

A tool for fixing a BibTeX reference list using DBLP API

reprohum-as-little-as-possible

Description of reproduction effort for Section 5.2. of https://aclanthology.org/2022.acl-short.53/

udapi-python

Python framework for processing Universal Dependencies data

ufal-tools

VariationalTemplateMachine

Code for "Variational Template Machine for Data-to-text generation"

videobook

whisper_streaming

Whisper realtime streaming for long speech-to-text transcription and translation