Parakeet VTDT 2.0 6B is NVIDIA's speech to text model. A 600M-parameter ASR model from NVIDIA's Parakeet family using TDT (Token-and-Duration Transducer) architecture, supporting punctuation, capitalization, and accurate English transcription.
nvidia-parakeet-vtdt-2-0-6b |
| Speech to Text |
| Active |
| Audio |
| Text |
| 0.6B |
Capabilities
Input1/5
·
·
✓
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Parakeet VTDT 2.0 6B | — | — | — | — | Current |
| Parakeet 1.1B CTC | — | — | — | — | Available |