Reference-aware automatic speech evaluation toolkit

PASQA: Pitch-Accent-Focused Speech Quality Assessment Model Trained on Synthetic Speech with Accent Errors

A lightweight, self-hostable tool for conducting subjective listening tests in a browser.

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…

Custom end4

Benchmarking STT service TTFB and semantic WER for real-time AI applications

Coco-Nut (Corpus of connecting NIHONGO utterance and text) corpus

Post-training with Tinker

Powerful system-level package manager for Linux, macOS and Windows written in Rust – building on top of the Conda ecosystem.

A fast, cross-platform build tool inspired by Make, designed for modern workflows.

AIST Toolkit for Accelerating Machine Learning Research

the runtime your coding agents live on

A toolkit for speaker diarization.

MoshiRAG is a compact full-duplex speech language model augmented with asynchronous knowledge retrieval to improve factuality without sacrificing real-time interactivity.

FlashCosyVoice: A lightweight vLLM implementation built from scratch for CosyVoice.

The agent that grows with you

Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)

Reference implementation of an end-to-end voice agent built using the NVIDIA Nemotron models

[EMNLP 2025 Findings] Code for "Distilling Many-Shot In-Context Learning into a Cheat Sheet"

List of open-source TTS, voice cloning, and music generation models