Tomoki Hayashi

alpagym. AlpaGym is a reinforcement-learning framework for end-to-end autonomous-driving policies.

asrlance. 「あすらんす」は音声認識性能を比較評価するツールです．音声ファイルパスと正解文を実行時に入力することで，認識精度（マイクロCER），処理にかかった時間，CPU使用率を結果として出力します．

LongCat-AudioDiT. Python

opensmile-python. Python package for openSMILE

prompt-review. Python

paperclip. The open-source app everyone uses to manage agents at work

joserfc. Implementations of JOSE RFCs in Python

MeanVC. A Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows

alpasim. AlpaSim is an open-source autonomous vehicle simulation platform designed for development and testing of end-to-end AV policies

DetZero. [ICCV 2023] DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds

Sidon. Training code and dataset cleasing with Sidon

3D-Speaker. A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization

valuecell. ValueCell is a community-driven, multi-agent platform for financial applications.

dcase-asd-toolkit. Python

uroman. Universal Romanizer that can convert any unicode script to roman (latin) script

claudecode.nvim. 🧩 Claude Code Neovim IDE Extension

spandsp. SpanDSP is a low-level signal processing library that modulates and demodulates signals commonly used in telephony, such as the "noise" generated by a fax modem or DTMF touchpad.

dia. A TTS model capable of generating ultra-realistic dialogue in one pass.

gptme. Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!

point-cloud-registration. Python

pyopenjtalk-plus. pyopenjtalk-plus: A Python wrapper for OpenJTalk with additional improvements

ollama_load_balancer. Autonomous Rust utility that load balances multiple https://ollama.com/ servers

OmniParser. A simple screen parsing tool towards pure vision based GUI agent

parler-tts. Inference and training library for high-quality TTS models.

YuE. YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

neoconf.nvim. 💼 Neovim plugin to manage global and project-local settings

kickstart.nvim. A launch point for your personal nvim configuration

awesome-mcp-servers. A collection of MCP servers.

Lotus. Official implementation of "Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction"

LightRAG. [EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

voice-changer. リアルタイムボイスチェンジャー Realtime Voice Changer

hubert. HuBERT content encoders for: A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion

insanely-fast-whisper. Jupyter Notebook

writer-framework. No-code in the front, Python in the back. An open-source framework for creating data apps.

litellm. The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

vits2_pytorch. unofficial vits2-TTS implementation in pytorch

aicommits. A CLI that writes your git commit messages for you with AI

delta. A syntax-highlighting pager for git, diff, grep, rg --json, and blame output

naturalspeech2-pytorch. Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch

gpt-pilot. The first real AI developer

miipher. Unofficial implementation of miipher

mlx. MLX: An array framework for Apple silicon

functionary. Chat language model that can use tools and interpret the results

llama-cpp-python. Python bindings for llama.cpp

stable-ts. Transcription, forced alignment, and audio indexing with OpenAI's Whisper

SpeechMOS. Easy-to-Use Speech MOS predictors

xtreme1. Xtreme1 is an all-in-one data labeling and annotation platform for multimodal data training and supports 3D LiDAR point cloud, image, and LLM.

JVSCorpusF0Range. JVSコーパスのF0探索範囲の詳細な調査結果

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Segment-Any-Anomaly. Official implementation of "Segment Any Anomaly without Training via Hybrid Prompt Regularization (SAA+)".

openinterpreter. A coding agent for open models like Kimi K3

stack-chan. A JavaScript-driven M5Stack-embedded super-kawaii robot.

facefusion. Industry leading face manipulation platform

local-llm-function-calling. A tool for generating function arguments and choosing what function to call with local LLMs

roslibpy. Python ROS Bridge library

openai-cookbook. Examples and guides for using the OpenAI API

XPhoneBERT. XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech (INTERSPEECH 2023)

ChatWaifu. Combined ChatGPT with Moegoe TTS to create a Chatting Waifu

ImageBind. ImageBind One Embedding Space to Bind Them All

tslearn. The machine learning toolkit for time series analysis in Python

spe-dss. Speech Parameter Estimation Using Differentiable Speech Synthesizer

octo.nvim. Edit and review GitHub issues and pull requests from the comfort of your favorite editor

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

VTuber-Python-Unity. An Implementation of VTuber (Both 3D and Live2D) using Python and Unity. Providing face movement tracking, eye blinking detection, iris detection and tracking and mouth movement tracking using CPU only.

AutoGPT. AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

alt-ime-ahk. AutoHotkey

ChatGPT.nvim. ChatGPT Neovim Plugin: Effortless Natural Language Generation with OpenAI's ChatGPT API

alqalign. multilingual speech aligner

supabase. The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.

edgeyolo. an edge-real-time anchor-free object detector with decent performance

pystoi. Python implementation of the Short Term Objective Intelligibility measure

Weighted-Boxes-Fusion. Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method.

peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

whisper.cpp. Port of OpenAI's Whisper model in C/C++

torch-yin. Yin pitch estimator in PyTorch

ReazonSpeech. Massive open Japanese speech corpus

nara_wpe. Different implementations of "Weighted Prediction Error" for speech dereverberation

nsxiv. Read-only mirror of Neo Simple X Image Viewer

cuml. cuML - RAPIDS Machine Learning Library

LoFTR. Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

RoadDamageDetector. Jupyter Notebook

NCEPLIBS-nemsio. The NCEPLIBS-nemsio library and utilities perform I/O for the NCEP models using NOAA Environmental Modeling System (NEMS) format.

ProDiff. PyTorch Implementation of ProDiff (ACM-MM'22) with a Extremely-Fast diffusion speech synthesis pipeline

Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

stable-diffusion. A latent text-to-image diffusion model

flamingo-pytorch. Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch

LAV. (CVPR 2022) A minimalist, mapless, end-to-end self-driving stack for joint perception, prediction, planning and control.

DeepPhonemizer. Grapheme to phoneme conversion with deep learning.

anomalib. An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

switch-scores. PDF Repository of switch score sheets.

pydtk. A Python toolkit for managing, retrieving and processing data.

onnx-model-encrypt-sample. ONNXモデルをpyca/cryptographyを用いて暗号化/復号化するサンプル

cryptography. cryptography is a package designed to expose cryptographic primitives and recipes to Python developers.

UTMOS22. UT-Sarulab MOS prediction system using SSL models

patchcore-inspection. Python

ginza. A Japanese NLP Library using spaCy as framework based on Universal Dependencies

dog-dataset. Python

pingu. 🐧ping command but with pingu

whylogs. An open-source data logging library for machine learning models and data pipelines. 📚 Provides visibility into data quality & model performance over time. 🛡️ Supports privacy-preserving data collection, ensuring safety & robustness. 📈

lm_build. Adapting your own Language Model for Kaldi

OSSGAN. Official implementation of OSSGAN [CVPR 2022]

diffsptk. A differentiable version of SPTK

PlotNeuralNet. Latex code for making neural networks diagrams

nvim-spectre. Find the enemy and replace them with dark power.

dashboard-nvim. vim dashboard

quickfix-reflector.vim. Change code right in the quickfix window

espnet_onnx. Onnx wrapper for espnet infrernce model

neural_prophet. NeuralProphet: A simple forecasting package

adamatch. Python

kubric. A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

pytorch_GAN_zoo. A mix of GAN implementations including progressive growing

date. Python

textlesslib. Library for Textless Spoken Language Processing

webvtt-py. Read, write, convert and segment WebVTT caption files in Python.

3detr. Code & Models for 3DETR - an End-to-end transformer model for 3D object detection

github-sponsors-tax. GitHub Sponsorsの確定申告手順

exkaldi-rt. An online speech recognition extension toolkit of Kaldi

searchbox.nvim. Start your search from a more comfortable place, say the upper right corner?

wenet. Production First and Production Ready End-to-End Speech Recognition Toolkit

torch-points3d. Pytorch framework for doing deep learning on point clouds.

cupoch. Robotics with GPU computing

probreg. Python package for point cloud registration using probabilistic model (Coherent Point Drift, GMMReg, SVR, GMMTree, FilterReg, Bayesian CPD)

Point-BERT. [CVPR 2022] Pre-Training 3D Point Cloud Transformers with Masked Point Modeling

silero-vad. Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Informer2020. The GitHub repository for the paper "Informer" accepted by AAAI 2021.

mdloader. Massdrop Firmware Loader - for CTRL / ALT / SHIFT / Rocketeer keyboards

Autoformer. About Code release for "Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting" (NeurIPS 2021), https://arxiv.org/abs/2106.13008

GMA. Learning to Estimate Hidden Motions with Global Motion Aggregation (ICCV 2021)

RAFT. Python

Multilingual_Text_to_Speech. An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.

fast_bss_eval. A fast implementation of bss_eval metrics for blind source separation

Image-Super-Resolution-via-Iterative-Refinement. Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch

VQMIVC. Official implementation of VQMIVC: One-shot (any-to-any) Voice Conversion @ Interspeech 2021 + Online playing demo!

textract. extract text from any document. no muss. no fuss.

mahalanobis_3d_multi_object_tracking. [NeurIPS Workshop 2019] Official code of the paper "Probabilistic 3D Multi-Object Tracking for Autonomous Driving." First Place of the First NuScenes Tracking Challenge in the AI Driving Olympics Workshop of NeurIPS.

vim-sh-heredoc-highlighting. Syntax highlighting for code snippets in shell heredocs

pyannote-audio. Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

grammarly. Grammarly for VS Code

wilder.nvim. A more adventurous wildmenu

clean-text. 🧹 Python package for text cleaning

sakai. Sakai is a freely available, feature-rich technology solution for learning, teaching, research and collaboration. Sakai is an open source software suite developed by a diverse and global adopter community.

tdmelodic. A Japanese accent dictionary generator

css10. CSS10: A Collection of Single Speaker Speech Datasets for 10 Languages

mmdetection3d. OpenMMLab's next-generation platform for general 3D object detection.

scenario_simulator_v2. A scenario-based simulation framework for Autoware

cvat. Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling services, for image, video, and 3D annotation with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.

ClassyVision. An end-to-end PyTorch framework for image and video classification

awesome-diarization. A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.

assem-vc. Official Code for Assem-VC @ICASSP2022

CenterFusion. CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection

ppg-vc. PPG-Based Voice Conversion

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

deep_sort_pytorch. MOT using deepsort and yolov3 with pytorch

pdfminer.six. Community maintained fork of pdfminer - we fathom PDF

dvc. 🦉 Data Versioning and ML Experiments

roc-star. Loss function which directly targets ROC-AUC

Kazakh_TTS. An expanded version of the previously released Kazakh text-to-speech (KazakhTTS) synthesis corpus. In KazakhTTS2, the overall size has increased from 93 hours to 271 hours, the number of speakers has risen from two to five (three females and two males), and the topic coverage has been diversified.

s3prl. Self-Supervised Speech Pre-training and Representation Learning Toolkit

speech-synthesis-paper. List of speech synthesis papers.

the-art-of-command-line. Master the command line, in one page

pytorch-softdtw-cuda. Fast CUDA implementation of (differentiable) soft dynamic time warping for PyTorch

vim-pydocstring. Generate Python docstring to your Python source code.

ConformerSED. Python

TTS. 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

byol-pytorch. Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch

audiomentations. A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.

lhotse. Tools for handling multimodal data in machine learning projects.

diff-so-fancy. Make your diffs human readable for improved code quality and faster defect detection. :tada:

quick-look-plugins. List of useful Quick Look plugins for developers

torchcrepe. Pytorch implementation of the CREPE pitch tracker

StreamingTransformer. Python

homebridge. HomeKit support for the impatient.

wemux. Multi-User Tmux Made Easy

vim-suda. 🥪 An alternative sudo.vim for Vim and Neovim, limited support sudo in Windows

scitldr. Python

LaboroTVSpeech. Shell

gluonts. Probabilistic time series modeling in Python

CenterPoint. Python

detectron2. Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

SiamMask. [CVPR19/TPAMI23] SiamMask: A Framework for Fast Online Object Tracking and Segmentation

textrank. TextRank implementation for Python 3.

gtn. Automatic differentiation with weighted finite-state transducers.

evaluation. A custom Rouge wrapper for summary evaluation.

darts. A python library for user-friendly forecasting and anomaly detection on time series.

prophet. Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.

hugo-bearblog. 🧸 A Hugo theme based on »Bear Blog«. Free, no-nonsense, super-fast blogging. This theme now includes a dark color scheme to support dark mode 🦉 ⬛️!

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

contiguous_pytorch_params. Accelerate training by storing parameters in one contiguous chunk of memory.

fugashi. A Cython MeCab wrapper for fast, pythonic Japanese tokenization and morphological analysis.

MatchSum. Code for ACL 2020 paper: "Extractive Summarization as Text Matching"

crank. A toolkit for non-parallel voice conversion based on vector-quantized variational autoencoder

AMFM_decompy. Package containing the tools necessary for decomposing a speech signal into its modulated components (also known as AM-FM decomposition). Includes the algorithms of the QHM family and the YAAPT pitch tracker.

sumeval. Well tested & Multi-language evaluation framework for text summarization.

blink. Blink Mobile Shell for iOS (Mosh based)

durian-pytorch. Implementation of "Duration Informed Attention Network for Multimodal Synthesis" paper in PyTorch.

pytorch-lightning. Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

phonemizer. Simple text to phones converter for multiple languages

TensorFlowTTS. :stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

glow-tts. A Generative Flow for Text-to-Speech via Monotonic Alignment Search

onssen. An open-source speech separation and enhancement library