Sosuke Kato's repositories
AudioMAE
This repo hosts the code and models of "Masked Autoencoders that Listen".
ctc-segmentation
Segment an audio file and obtain utterance alignments. (Python package)
daachorse
🐎 A fast implementation of the Aho-Corasick algorithm using the compact double-array data structure in Rust.
deep-learning-containers
AWS Deep Learning Containers (DLCs) are a set of Docker images for training and serving models in TensorFlow, TensorFlow 2, PyTorch, and MXNet.
detectron2
Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks.
doccano
Open source annotation tool for machine learning practitioners.
espnet_tts_frontend
Text frontend for ESPnet tts recipes
fast-ctc-decode
Blitzing Fast CTC Beam Search Decoder
flashlight
A C++ standalone library for machine learning
gecko
Gecko - A Tool for Effective Annotation of Human Conversations
haystack
:mag: Haystack is an open source NLP framework that leverages pre-trained Transformer models. It enables developers to quickly implement production-ready semantic search, question answering, summarization and document ranking for a wide range of NLP applications.
inflection
A port of Ruby on Rails' inflector to Python
ParallelWaveGAN
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
pydantic
Data parsing and validation using Python type hints
pyroomacoustics
Pyroomacoustics is a package for audio signal processing for indoor applications. It was developed as a fast prototyping platform for beamforming algorithms in indoor scenarios.
remdis
The Remdis toolkit: Building advanced real-time multimodal dialogue systems with incremental processing and large language models
s3prl
Self-Supervised Speech Pre-training and Representation Learning Toolkit.
smui-example-sveltekit
SMUI SvelteKit Example
streamp3
Streaming MP3 decoder for Python
SudachiTra
Japanese tokenizer for Transformers
svelte-historyapi-routing-example
An example project implementing Svelte SPA with Mobile Apps-like transitions using History API.
svelte-touch-driven-draggable-example
A Svelte example that enables D'n'D API to work with Touch Event
textspan
Text span utilities for Rust and Python
unilm
UniLM - Unified Language Model Pre-training / Pre-training for NLP and Beyond
VBx
Variational Bayes HMM over x-vectors diarization
wavesurfer-react
A simple React wrapper for wavesurfer.js
wavesurfer.js
Navigable waveform built on Web Audio and Canvas