Canary (NVIDIA NeMo)

Multilingual ASR model by NVIDIA supporting 4 languages with translation.

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

About

Canary by NVIDIA NeMo is a multilingual automatic speech recognition model that both transcribes and translates speech, originally covering English, German, French, and Spanish and extended in later versions to more languages with lower word error rates. It is built on the NeMo speech framework with open weights and demos on Hugging Face. Released under the Apache 2.0 license.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

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

Related Tools

Whisper extension providing word-level timestamps for transcription.

Open SourceSelf HostedOfflineGPU 4GB+
Easy
0.0 (0)

Convolution-augmented transformer for speech recognition in ESPnet toolkit.

Open SourceSelf HostedOfflineGPU 8GB+
Advanced
0.0 (0)

Pre-trained speech models for STT, TTS, and VAD with simple PyTorch integration.

Open SourceSelf HostedOffline
Beginner
0.0 (0)

CLI tool that transcribes audio 10x faster using pipeline optimizations.

Open SourceSelf HostedOfflineGPU 6GB+
Easy
0.0 (0)

Self-supervised speech representation model by Meta for ASR.

Open SourceSelf HostedOfflineGPU 8GB+
Advanced
0.0 (0)

Open-source speaker diarization and voice activity detection toolkit.

Open SourceSelf HostedOfflineGPU 4GB+
Intermediate
0.0 (0)
Browse all Speech-to-Text / Speech Recognition tools