syhw

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

timit_tools. tools around preparing TIMIT for HMM (with HTK) and deep learning (with Theano) methods

DL4H. Deep learning for hackers: a hands-on approach to machine learning and deep learning.

BroodwarBotQ. A Starcraft: Broodwar bot using BWAPI

speech_embeddings. Using embedding-based loss functions for phonetics/speech recognition.

homebrew. my homebrew kegs/ports

bwrepdump. Broodwar replays dumper (using BWAPI)

Broodwar_replays_scrappers. A collection of scrappers for replays sites

RTS_AI_survey. Managing the latex and bibliography files for a survey paper on RTS AI techniques

OpeningTech. Opening tech prediction through machine learning for Starcraft AI

HN_stats. Pulls articles from HN, builds a topic model with Gensim (from Wikipedia+HN), can tune HN to users.

abnet. ABNet is a "same/different"-based loss trained neural net.

regatta-bot. A bot for virtual-regatta

AnalyzeBWData. tools to analyze Broodwar Data

DTW_Cython. Dynamic Time Warping in Cython

snippyhollow.github.com. JavaScript

contextual_word_segmentation. Unsupervised word segmentation from phonemes, using activity contexts (topics)

pruning_phrase_table. Python implementation of Improving Translation Quality by Discarding Most of the Phrasetable (Johnson, Martin, Foster, Kuhn 2007)

syhw-phd-thesis. my Ph.D thesis

Dotfiles. Vim Script

binaural_from_surround. Binaural audio (for headphones) from surround sound.

Replayer. Starcraft replay analyser with BWAPI

py-tsdisc. time-series discretization in python

kegg2symb. convert from KEGG XML&API queries to a logical symbolic model

hnewsfr. hacker news francophone

Potato. Google Contacts Sharing

RestoPhoto. Restaurant reviews from picture on Android.

caffe. Caffe: a fast framework for deep learning. For the most recent version checkout the dev branch. For the latest stable release checkout the master branch.

dota2_stats. Stats about dota 2

KodeKatas. katas to train vim and to train new languages

synth_imit. Synthetic TIMIT

heathcare_bootcamp. Python

gpsych. Gaussian processes for psychometric curves regression.

autogradpp. Direct C++ Interface to PyTorch

encodec. State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

mosileno. Hacking hacker news results for more efficient procrastination!

Config-files. versionning of my config files

clusterize_RTS_data. Clusterize all kinds of data from real-time strategy games

StarcraftAITournamentManager. Tournament Manager Software for StarCraft AI Competitions

blog.emillon.org. My blog, written using Hakyll

audiocraft. Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

vowpal_wabbit. John Langford's original release of Vowpal Wabbit -- a fast online learning algorithm

scikit-learn. scikit-learn: machine learning in Python

h5py. HDF5 for Python -- The h5py package is a Pythonic interface to the HDF5 binary data format.

toying_with_BNP. Python

prob2tikz. Probas to TikZ