NVIDIA NeMo ASR

Production-grade ASR models and toolkit by NVIDIA for speech recognition.

Open SourceSelf HostedOffline CapableGPU Required (8GB+ VRAM)
0.0 (0)

About

NVIDIA NeMo is a toolkit for building and training conversational AI models. The ASR collection includes production-grade speech recognition models (Conformer, FastConformer, Canary) supporting 100+ languages. Requires NVIDIA GPU. Apache 2.0 license.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Advanced (4/5)
License
Apache-2.0
Minimum VRAM
8 GB
Added
Apr 3, 2026

Similar Tools

Featured

General-purpose speech recognition model by OpenAI trained on 680K hours of multilingual audio.

Open SourceSelf HostedOffline
Easy
0.0 (0)
Featured

High-performance C/C++ port of Whisper for CPU-based speech recognition.

Open SourceSelf HostedOffline
Easy
0.0 (0)

Offline speech recognition toolkit supporting 20+ languages with small models.

Open SourceSelf HostedOffline
Easy
0.0 (0)