Automatic Speech Recognition
NeMo
PyTorch
automatic-speech-translation
speech
audio
Transformer
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use nvidia/canary-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/canary-1b with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/canary-1b") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Update README.md
#9
by steveheh - opened
README.md
CHANGED
|
@@ -470,7 +470,7 @@ More details on evaluation can be found at [HuggingFace ASR Leaderboard](https:/
|
|
| 470 |
|
| 471 |
### AST Performance
|
| 472 |
|
| 473 |
-
We evaluate AST performance with BLEU score and use
|
| 474 |
|
| 475 |
BLEU score on [FLEURS](https://huggingface.co/datasets/google/fleurs) test set:
|
| 476 |
|
|
|
|
| 470 |
|
| 471 |
### AST Performance
|
| 472 |
|
| 473 |
+
We evaluate AST performance with [BLEU score](https://lightning.ai/docs/torchmetrics/stable/text/sacre_bleu_score.html), and use native annotations with punctuation and capitalization in the datasets.
|
| 474 |
|
| 475 |
BLEU score on [FLEURS](https://huggingface.co/datasets/google/fleurs) test set:
|
| 476 |
|