Automatic Speech Recognition
NeMo
Safetensors
PyTorch
fastconformer
automatic-speech-translation
speech
audio
Transformer
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use nvidia/canary-1b-flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/canary-1b-flash with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/canary-1b-flash") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
| { | |
| "_filterbanks": null, | |
| "f_max": 8000, | |
| "f_min": 0, | |
| "feature_extractor_type": "FastConformerFeatureExtractor", | |
| "feature_size": 128, | |
| "hop_length": 160, | |
| "mag_power": 2.0, | |
| "mel_norm": "slaney", | |
| "mel_scale": "htk", | |
| "n_fft": 512, | |
| "n_mels": 128, | |
| "normalize": "per_feature", | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "preemph": 0.97, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000, | |
| "win_length": 400, | |
| "window_size": 0.025, | |
| "window_stride": 0.01 | |
| } | |