Model
Jasper TorchScript model in FP16 format trained with AMP on LibriSpeech
Use the NGC CLI to download:
Copied!
1 Version
20.10.0Selected02/10/2021 12:32 AM UTC581.57 MBAccuracy: 0440 EpochsBatch Size: 512GPU: A100 Copied!
20.10.0Selected
02/10/2021 12:32 AM UTC581.57 MBAccuracy: 0440 EpochsBatch Size: 512GPU: A100
Copied!
architecture
| Key | Value |
|---|---|
| type | jasper10x5dr_speedp-online_speca: SpecAugment (2x20, 3x75); Speed perturbation U(0.85, 1.15) |
performance
| Key | Value |
|---|---|
| dev_clean_wer | 3.20 |
| dev_other_wer | 9.74 |
| test_clean_wer | 3.38 |
| test_other_wer | 9.66 |
training
| Key | Value |
|---|---|
| batch_size | 512 |
| dataset | LibriSpeech |
| epochs | 440 |
| training_precision | AMP |