Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong Audio Event Taggers"
- audio
- audio-classification
- audio-processing
- audio-tagging
54,641 visible repositories in the index
73–96 of 153 · Most stars
Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong Audio Event Taggers"
Plan and apply Terraform/OpenTofu via PR automation, using best practices for secure and scalable IaC workflows.
HALO: Perceptive Humanoid Motion from Simulation
A Neovim diff viewer that preserves each document’s natural shape and line numbers, using connector gutters to map changes without inline diff noise.
No-jailbreak iOS privacy, entitlement, sandbox & telemetry forensic auditor (inspired by Verlintas/NOIR)
Erlang LSM BTree Storage
Ear-bending noises and music
Very fast, high-quality hash function, discrete-incremental and streamed hashing-capable (non-cryptographic, header-only C/C++) 27GB/s + PRNG
SuperMimic-UniLab: An Independent reproduction of SuperMimic on UniLab for whole-body humanoid motion tracking.
gNXI Tools - gRPC Network Management/Operations Interface Tools
Opinionated paranoid text spacing in Python
Voronoi / Delaunay tessellations on the sphere
Rails Plugin - soft-delete your ActiveRecord records. It's like an explicit version of ActsAsParanoid
Tutorial on making a full-featured arkanoid (breakout)-type game with LÖVE framework.
Elixir port of NanoID, a secure and URL-friendly unique ID generator. https://hex.pm/packages/nanoid
Android Interview Questions
D3 plugin which computes a treemap based on a Voronoi tesselation
High-performance Prefix KV Caching & Streaming Long Video Suite for MiniMax H3 in ComfyUI
Remove the fish-scale noise GPT image models leave in anime / TV-anime images (ESRGAN @60% + L0 smoothing)
Whole-body motion tracking for the Unitree G1 in about 3 minutes on one GPU.
gRPC Network Operations Interface (gNOI) defines a set of gRPC-based microservices for executing operational commands on network devices.
Whole-body motion tracking for the Unitree G1 in under 3 minutes on average on one GPU: return 0.82 with 0/40 clips failed, held from 2.74 min (mean of 15 seeds, range 2.21-3.61, fine checkpoints), 11.87 it/s (world model + Muon + overlapped CUDA streams, mjlab)
Go implementation of noisy HTTP/DNS traffic generator
🏃 The go-to single-cell Foundation Model