Speech
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
HYSEN LABS ディレクトリ
NVIDIA-NeMo組織の検証済みリポジトリ、分類、分析。
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.
🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.
プロジェクト概要:効率的にモデルを強化するためのスケーラブルなツールキット。 [2026/04/06] 新しいモデルのサポート GRPO トレーニング用の Qwen3.5 密モデルおよび MoE モデル (LLM および VLM) のサポートが追加されました。
Scalable data pre processing and curation toolkit for LLMs
Evaluate and improve models and agents using environments
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support