YoshikiMas

speechmetrics

A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR

PAM

PAM is a no-reference audio quality metric for audio generation tasks

mistral-finetune

SciencePlots

Matplotlib styles for scientific plotting

Open-GPT-4o

gammachirpy

A Python package of the dynamic compressive gammachirp filterbank (dcGC-FB)

ThunderKittens

Tile primitives for speedy kernels

KANeRF

KAN-based NeRF

EvalAI

:cloud: :rocket: :bar_chart: :chart_with_upwards_trend: Evaluating state of the art in AI

ispa

agentops

Python SDK for agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks like CrewAI, Langchain, and Autogen

HRTF-upsampling-with-a-generative-adversarial-network-using-a-gnomonic-equiangular-projection

LAPChallenge

The LAP Challenge aims at advancing spatial audio technologies through the personalization of HRTFs.

insanely-fast-whisper

dcase2024_task9_baseline

Baseline for DCASE 2024 Task 9: "Language-Queried Audio Source Separation"

awesome-whisper

🔊 Awesome list for Whisper — an open-source AI-powered speech recognition system developed by OpenAI

pghipy

STFT/ISTFT transforms and phase recovery using phase gradient heap integration

hartufo

A Python toolkit for data-driven HRTF research

WavCraft

Official repo for WavCraft, an AI agent for audio creation and editing

seamless_communication_emo

Foundational Models for State-of-the-Art Speech and Text Translation

DTTNet-Pytorch

An official implementation of the ICASSP 2024 paper: Dual-Path TFC-TDF UNet for Music Source Separation

Swin-Transformer-1d

PyTorch implementation of Swin Transformer for 1-dimensional data

Amphion

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

NLP2024-tutorial-3

NLP2024 チュートリアル３ 作って学ぶ日本語大規模言語モデル - 環境構築手順とソースコード / NLP2024 Tutorial 3: Practicing how to build a Japanese large-scale language model - Environment construction and experimental source codes

HiddenMambaAttn

Official PyTorch Implementation of "The Hidden Attention of Mamba Models"

sumeval

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

brouhaha-vad

Predicts the level of noise and reverberation on your audiofiles

Codec-SUPERB

Audio Codec Speech processing Universal PERformance Benchmark

sacred

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

SoundCard

A Pure-Python Real-Time Audio Library