NeMo

Overview

NeMo is a scalable generative AI framework for researchers and developers building large language models, multimodal systems, and speech AI applications including automatic speech recognition and text-to-speech. It provides Python-based tooling for training and deploying these models, with a large open-source community.

Best for

Best for
Researchers and developers building speech and multimodal AI systems

Use cases

• Training custom automatic speech recognition models
• Developing text-to-speech systems
• Building multimodal generative AI models

Notes

NeMo is a scalable generative AI framework for researchers and developers building large language models, multimodal systems, and speech AI applications including automatic speech recognition and text-to-speech. It provides Python-based tooling for training and deploying these models, with a large open-source community.

18,379 stars on GitHub. Last updated 2026-09-02. Licensed Apache-2.0.

Use cases

• Training custom automatic speech recognition models
• Developing text-to-speech systems
• Building multimodal generative AI models

Pros

• Open source with strong community support (18k+ stars)
• Scalable framework for production-grade models
• Covers multiple AI domains including LLM, multimodal, and speech

Cons

• Requires significant GPU resources for training
• Complex setup and configuration
• Steep learning curve for beginners

Indexed from awesome-generative-ai and enriched against its public facts.