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
Fixed type .trancribe -> .transcribe
Browse files
README.md
CHANGED
|
@@ -312,7 +312,7 @@ canary_model.change_decoding_strategy(decode_cfg)
|
|
| 312 |
The input to the model can be a directory containing audio files, in which case the model will perform ASR on English and produces text with punctuation and capitalization:
|
| 313 |
|
| 314 |
```python
|
| 315 |
-
predicted_text = canary_model.
|
| 316 |
audio_dir="<path to directory containing audios>",
|
| 317 |
batch_size=16, # batch size to run the inference with
|
| 318 |
)
|
|
|
|
| 312 |
The input to the model can be a directory containing audio files, in which case the model will perform ASR on English and produces text with punctuation and capitalization:
|
| 313 |
|
| 314 |
```python
|
| 315 |
+
predicted_text = canary_model.transcribe(
|
| 316 |
audio_dir="<path to directory containing audios>",
|
| 317 |
batch_size=16, # batch size to run the inference with
|
| 318 |
)
|