Automatic Speech Recognition
NeMo
Safetensors
PyTorch
canary
automatic-speech-translation
speech
audio
Transformer
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Transformers
Eval Results (legacy)
Eval Results
Instructions to use nvidia/canary-1b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/canary-1b-v2 with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/canary-1b-v2") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Commit History
-
feat(transformers): Add native Transformers weights and usage (#27)
- Upload processor (d3ef700a1215f51ec4be07530227493f1ea1726c) - Upload CanaryForConditionalGeneration (47096af7916100df8976fc56eb67a4dd933f2ae0) - Update with Transformers usage (11c668d0f26143cdab7e2bdb4617582cdc0fa4c9) - Update config with decoder sub-config (ba848697163bb5c013c0aaddc4b3b9f9a2f29767) - Update decoder state dict with CohereAsrDecoder layout (be5326470a63986b1c495446f65843759682c869) - Update training example to use output_labels (866e8c144834f3bb7f73ffe111e78a1ad0d9b101) Co-authored-by: Harshal Janjani <harshaljanjani@users.noreply.huggingface.co>d455706