kahne

Changhan Wang's starred repositories

algorithm-visualizer

:fireworks:Interactive Online Platform that Visualizes Algorithms from Code

Language:JavaScriptMIT46105 1231 112

tensor2tensor

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

Language:PythonApache-2.014868 465 1247

flair

A very simple framework for state-of-the-art Natural Language Processing (NLP)

Language:PythonNOASSERTION13558 202 2257

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.

Language:C++NOASSERTION8400 349 1264

awesome-self-supervised-learning

A curated list of awesome self-supervised methods

5978 246 19

openmlsys-zh

《Machine Learning Systems: Design and Implementation》- Chinese Version

Language:TeX3648 47 201

aeneas

aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)

Language:PythonAGPL-3.02389 75 209

wer_are_we

Attempt at tracking states of the arts and recent results (bibliography) on speech recognition.

1866 220 22

magnitude

A fast, efficient universal vector embedding utility package.

Language:PythonMIT1610 38 84

voice_datasets

🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).

1528 43 17

open-speech-corpora

💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies

MIT1208 57 199

alfred

alfred-py: A deep learning utility library for **human**, more detail about the usage of lib to: https://zhuanlan.zhihu.com/p/341446046

Language:PythonGPL-3.0883 21 27

epitran

A tool for transcribing orthographic text as IPA (International Phonetic Alphabet)

Language:PythonMIT575 22 92

voxpopuli

A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation

Language:PythonNOASSERTION491 18 22

Phonetisaurus

Phonetisaurus G2P

Language:ShellBSD-3-Clause430 33 55

COMET

A Neural Framework for MT Evaluation

Language:PythonApache-2.0394 17 147

DME

Dynamic Meta-Embeddings for Improved Sentence Representations

Language:PythonNOASSERTION332 18 7

g2pm

A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset

Language:PythonApache-2.0326 15 18

covost

CoVoST: A Large-Scale Multilingual Speech-To-Text Translation Corpus (CC0 Licensed)

Language:PythonNOASSERTION320 20 4

DeepPhonemizer

Grapheme to phoneme conversion with deep learning.

Language:PythonMIT319 21 31

NonAutoregGenProgress

Tracking the progress in non-autoregressive generation (translation, transcription, etc.)

CC0-1.0305 28 1

neurst

Neural end-to-end Speech Translation Toolkit

Language:PythonNOASSERTION293 15 23

CharsiuG2P

Multilingual G2P in 100 languages

Language:Jupyter NotebookMIT245 10 10

SpeechTransProgress

Tracking the progress in end-to-end speech translation

CC0-1.0238 26 2

fastwer

A PyPI package for fast word/character error rate (WER/CER) calculation

Language:PythonMIT66 2 9

eskmeans

Embedded segmental K-means (ES-KMeans) in Python.

Language:PythonGPL-3.013 2 2