juice500ml

dysarthria-gop

xlm_to_xlsr

Official implementation of the paper "Distilling a Pretrained Language Model to a Multilingual ASR Model" (Interspeech 2022)

dysarthria-mtl

unbox-w2v-convnet

Official implementation of the paper, "Opening the Black Box of wav2vec Feature Encoder."

information_probing

juice500ml.github.io

juice500ml's blog

phonetic_semantic_probing

finetune_owsm

Finetuning for ESPNet OWSM Model

audiomentations

A Python library for audio data augmentation. Inspired by albumentations. Useful for machine learning.

changelinglab.github.io

Website for the CMU Language Change and Empirical Linguistics Lab

click

Python composable command line utility

dynamic-superb

The official repository of Dynamic-SUPERB.

enas

TensorFlow Code for paper "Efficient Neural Architecture Search via Parameter Sharing"

espnet

End-to-End Speech Processing Toolkit

flask

The Python micro framework for building web applications.

gugugu

An open-chat service w/ some hip, happenin' UI—mostly for seminar Q&As.

jupyter_contrib_nbextensions

A collection of various notebook extensions for Jupyter

KILT

Library for Knowledge Intensive Language Tasks

ldc_downloader

Script to download corpora from the Linguistic Data Consortium (LDC)

linguistic-superb

mgcpp

A C++ Math Library Based on CUDA

mixed_KSG

notebook

panphon

Python package and data files for manipulating phonological segments (phones, phonemes) in terms of universal phonological features.

s3transfer

Amazon S3 Transfer Manager for Python

SemiNAS

Semi Supervised Neural Architecture Search

shinjiwlab.github.io

text-anomaly-detection

TiDAL

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.