Model
NeMo Speech Models include speech recognition, command recognition, speaker identification, speaker verification and voice activity detection. These models are used for Automatic Speech Recognition (ASR) and sub-tasks.
Use the NGC CLI to download:
Copied!
| Name | Size | Updated | Actions |
|---|---|---|---|
ContextNet-192-WPE-1024-8x-Stride.nemo | 49.85 MB | February 28, 2025 UTC | |
Jasper10x5Dr-En.nemo | 1.15 GB | February 28, 2025 UTC | |
MatchboxNet_VAD_3x2.nemo | 368 KB | February 28, 2025 UTC | |
MatchboxNet-3x1x64-v1.nemo | 310.71 KB | February 28, 2025 UTC | |
MatchboxNet-3x1x64-v2-subset-task.nemo | 303.76 KB | February 28, 2025 UTC | |
MatchboxNet-3x1x64-v2.nemo | 314.16 KB | February 28, 2025 UTC | |
MatchboxNet-3x2x64-v1.nemo | 371.77 KB | February 28, 2025 UTC | |
MatchboxNet-3x2x64-v2-subset-task.nemo | 363.79 KB | February 28, 2025 UTC | |
MatchboxNet-3x2x64-v2.nemo | 374.85 KB | February 28, 2025 UTC | |
QuartzNet15x5Base-En.nemo | 67.79 MB | February 28, 2025 UTC | |
QuartzNet15x5Base-Zh.nemo | 87.16 MB | February 28, 2025 UTC | |
QuartzNet15x5NR-En.nemo | 67.82 MB | February 28, 2025 UTC | |
QuartzNet5x5LS-En.nemo | 24.06 MB | February 28, 2025 UTC | |
SpeakerNet_recognition.nemo | 30.9 MB | February 28, 2025 UTC | |
SpeakerNet_verification.nemo | 30.88 MB | February 28, 2025 UTC |