Josef's starred repositories
100-Days-Of-ML-Code
100 Days of ML Coding
google-research
Google Research
NLP-progress
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
Data-Analysis
Data Science Using Python
ParallelWaveGAN
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
UnsupervisedMT
Phrase-Based & Neural Unsupervised Machine Translation
CTCDecoder
Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon search, prefix search, and token passing. Implemented in Python.
audio-annotator
A JavaScript interface for annotating and labeling audio files.
autoEdit_2
Fast text based video editing, node Electron Os X desktop app, with Backbone front end.
open-speech-recording
Web application to record speech for an open data set
DistanceGAN
Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017
vcc20_baseline_cyclevae
Voice Conversion Challenge 2020 CycleVAE baseline system
word-embeddings-for-nmt
Supplementary material for "When and Why Are Pre-trained Word Embeddings Useful for Neural Machine Translation?" at NAACL 2018
FrameTrail
FrameTrail is an open source software that let's you experience, manage and edit interactive video directly in your web browser. It enables you to hyperlink filmic contents, include additional multimedia documents (e.g. text overlays, images or interactive maps) and to add supplementing materials (annotations) at specific points.
speech2vec-pretrained-vectors
Speech2vec pre-trained word vectors
ml-deployment-demo
ML Deployment, Two Ways
audio_degrader
Audio degradation toolbox in python, with a command-line tool. It is useful to apply controlled degradations to audio: e.g. data augmentation, evaluation in noisy conditions, etc.
ffmpeg-commands
Collection of useful FFMPEG commands for processing audio and video files.