NVIDIA-NeMo/Speech

★18,727PythonApache-2.0⑂ 3,685Issue 142Updated Nov 11, 2026

View on GitHub ↗Website ↗

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)

NVIDIA splits off a dedicated Speech AI framework from NeMo — NeMo Speech 3.0 is a newly spun-off repo focused solely on ASR, TTS, and speech translation, separated from the broader NeMo project. Recent releases include multilingual MagpieTTS, a streaming ASR model supporting 40 languages with sub-second latency, and a unified English model combining offline and streaming inference in one checkpoint.

Metrics

Retention can be computed 30 days after a repository first trends (it isn't shown until then). See About for how each metric is defined.

Star growth and Trending appearances (last 30 days)

Created Aug 6, 2019 · First on trending Oct 31, 2026

Other notable repositories in the same category (LLMs & ML)

• snap-stanford/memorillaCompressing Entire Document Collections into 16 Memory Tokens
• kerlenton/bootgptA Tiny Neural Net That Boots Straight From the MBR
• scienthoon/jev-ood-calibrationTesting Whether Jev's Confidence Scores Stay Honest Out-of-Distribution
• alejandrohdez00/alien-space-of-scienceSampling research ideas that are coherent but hard for humans to reach
• microsoft/VibeVoiceMicrosoft's open voice AI grows into streaming speech recognition

See all LLMs & ML repositories →

Rank within generative-ai

See all generative-ai repositories →