-
The University of Electro-Communications
- Tokyo
-
19:54
(UTC +09:00) - @y_chan_dev
Highlights
- Pro
Stars
Officail repo for SingMOS-Pro (ICASSP 2026)
[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling
Vector (and Scalar) Quantization, in Pytorch
[ICLR 2026] Official implementation of Toward Complex-Valued Neural Networks for Waveform Generation
Cross-platform GPU texture sharing for Electron: Spout (Win) + Syphon Metal (Mac)
🐹 Clean, uninstall, analyze, optimize, and monitor your Mac from the terminal.
The Official PyTorch Implementation of "Poisson Variational Autoencoder" (NeurIPS 2024 Spotlight Paper)
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
Multicamera Calibration for Motion Capture Workflows
Gradient Reversal Layer for Domain Adaptation
Pear 🍐 is extension for music player
Elliptic Curve Integrated Encryption Scheme for secp256k1/curve25519 in TypeScript
セキュリティキャンプ2024全国大会 D2講義「クラウドソーシングによる学習データ作成と品質管理」のハンズオン資料
PyTorch implementation of WaveFit [2022, Google] which is one of SOTA lightweight/fast speech vocoders.
学務情報システム上で必要単位数を満たしているかを一発で確認するブックマークレット
Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch
Open source hyperconverged infrastructure (HCI) software
Japanese text preprocessor for Text-to-Speech applications (OpenJTalk rewrite in rust language)