Model
Jasper models are end-to-end neural automatic speech recognition (ASR) models that transcribe segments of audio to text.
Use the NGC CLI to download:
Copied!
1 Version
1.0.0rc1Selected03/10/2021 2:28 AM UTC1.15 GB Copied!
1.0.0rc1Selected
03/10/2021 2:28 AM UTC1.15 GB
Copied!
Accuracy
| Key | Value |
|---|---|
| dev-clean | 3.74 |
| dev-other | 10.21 |
Model
| Key | Value |
|---|---|
| Architecture | Jasper |
| Inputs | 16000 KHZ MONO-CHANNEL AUDIO (WAV FILES) |
| Outputs | Transcription text |