Automatic Speech Recognition
NeMo
PyTorch
Kinyarwanda
speech
audio
CTC
Conformer
Transformer
NeMo
hf-asr-leaderboard
Riva
Eval Results (legacy)
Instructions to use nvidia/stt_rw_conformer_ctc_large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/stt_rw_conformer_ctc_large with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/stt_rw_conformer_ctc_large") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -76,7 +76,8 @@ asr_model = nemo_asr.models.EncDecCTCModelBPE.from_pretrained("nvidia/stt_rw_con
|
|
| 76 |
### Transcribing using Python
|
| 77 |
Simply do:
|
| 78 |
```
|
| 79 |
-
asr_model.transcribe(['
|
|
|
|
| 80 |
```
|
| 81 |
|
| 82 |
### Transcribing many audio files
|
|
|
|
| 76 |
### Transcribing using Python
|
| 77 |
Simply do:
|
| 78 |
```
|
| 79 |
+
output = asr_model.transcribe(['sample.wav'])
|
| 80 |
+
print(output[0].text)
|
| 81 |
```
|
| 82 |
|
| 83 |
### Transcribing many audio files
|