Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | nvidianvidia/parakeet-tdt-0.6b-v2Remove × |
|---|---|
| What’s different | 0.6B parameters · Encoder: Conformer-based · Decoder: TDT / RNN-T |
| Date | Oct 17, 2026Discovered |
API prices USD · provider configuration shown below | |
| Listed rate | See provider quotes |
| Provider endpoints | 0 endpoints → |
Benchmarks Each result retains its evaluation configuration | |
| AMI-Cleaned WER ↗English short-form; normalization unversioned | 9.09% WER ↗nvidia/parakeet-tdt-0.6b-v2Leaderboard entry |
| Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned | 6.76% WER ↗nvidia/parakeet-tdt-0.6b-v2Leaderboard entry |
| Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned | 8.15% WER ↗nvidia/parakeet-tdt-0.6b-v2Leaderboard entry |
| LS Clean WER ↗English short-form; normalization unversioned | 1.28% WER ↗nvidia/parakeet-tdt-0.6b-v2Leaderboard entry |
| LS Other WER ↗English short-form; normalization unversioned | 2.73% WER ↗nvidia/parakeet-tdt-0.6b-v2Leaderboard entry |
| SPGISpeech WER ↗English short-form; normalization unversioned | 1.94% WER ↗nvidia/parakeet-tdt-0.6b-v2Leaderboard entry |
| URGENT2024 WER ↗English short-form; normalization unversioned | 11.42% WER ↗nvidia/parakeet-tdt-0.6b-v2Leaderboard entry |
| Voice Arena Monsoon WER ↗English short-form; normalization unversioned | 3.89% WER ↗nvidia/parakeet-tdt-0.6b-v2Leaderboard entry |
| Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned | 3.78% WER ↗nvidia/parakeet-tdt-0.6b-v2Leaderboard entry |
Specifications | |
| Context window | — |
| Max output | — |
| Parameters | 0.6B |
| Audio input | Supported |
| Transcription | Supported |