NVIDIA-NeMo/Speech

Speech

✅ Recently maintained

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)

18,685Stars
3,675Forks
+657-day stars

Python · Apache-2.0 · Last push 2026-11-02

Official repository & installation ↗
machine-translationspeaker-recognitionasrttsgenerative-aideeplearningneural-networksspeaker-diariazationspeech-translationspeech-synthesis

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2025-09-292026-11-03
View historical data
DateStars
2026-10-0518,529
2026-10-0618,534
2026-10-0718,539
2026-10-0818,544
2026-10-0918,546
2026-10-1018,551
2026-10-1118,552
2026-10-1218,555
2026-10-1318,560
2026-10-1418,566
2026-10-1518,574
2026-10-1618,578
2026-10-1718,584
2026-10-1818,589
2026-10-1918,592
2026-10-2018,597
2026-10-2118,601
2026-10-2218,603
2026-10-2318,607
2026-10-2418,609
2026-10-2518,615
2026-10-2618,619
2026-10-2718,622
2026-10-2818,636
2026-10-2918,649
2026-10-3018,656
2026-10-3118,663
2026-11-0118,676
2026-11-0218,681
2026-11-0318,685

Get the project

git clone https://github.com/NVIDIA-NeMo/Speech.git

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

silero-models

Silero Models: pre-trained text-to-speech models made embarrassingly simple

★ 6,160VoiceStudio

A fully local open-source voice studio for cloning, dubbing, transcription and audiobook creation across 646 languages.

★ 99,350unsloth

Finetune Llama, Mistral and other LLMs 2-5x faster with 80% less memory.

★ 78,988