Model
Conformer-Transducer-Large model for Kinyarwanda Automatic Speech Recognition, trained on Mozilla Common Voice 9.0 Kinyarwanda dataset.
Use the NGC CLI to download:
Copied!
1 Version
1.11.0Selected07/21/2022 10:00 PM UTC460.15 MB Copied!
1.11.0Selected
07/21/2022 10:00 PM UTC460.15 MB
Copied!
Accuracy
| Key | Value |
|---|---|
| MCV_9.0 | 16.2 % |
Model
| Key | Value |
|---|---|
| ARCHITECTURE | Conformer-Transducer |
| INPUTS | 16000 KHZ MONO-CHANNEL AUDIO (WAV FILES) |
| OUTPUTS | TRANSCRIBED SPEECH |