AI + Data, online. https://vespa.ai

LongCat Audio Tokenizer and Detokenizer

Retrieval-Augmented MOS Prediction with Prior Knowledge Integration

The best ChatGPT that $100 can buy.

A Python implementation of FastDTW

[ICLR 2025] OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation

Kroko ASR - Speech-to-text

This repo contains the source code for the paper "Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning"

A novel data compression framework

https://hf.co/hexgrad/Kokoro-82M

Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

On-device TTS model by Neuphonic

IIR Hilbert filter: short, dependency-free, header-only C++

Cloud AI live transcription and translation service plugin

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

A general purpose task-agnostic speech augmentation policy

[NeurIPS 2024] VFIMamba: Video Frame Interpolation with State Space Models

VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latency

Banquet: A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems

RAM is all you need

Audio decoding libraries for C/C++, each in a single source file.

Fast, modern C++ DSP framework, FFT, Sample Rate Conversion, FIR/IIR/Biquad Filters (SSE, AVX, AVX-512, ARM NEON)

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Optimized primitives for collective multi-GPU communication

common in-memory tensor structure

A feature-rich command-line audio/video downloader