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-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
Fine‑tune Canary‑1b‑v2
#16
by Filipblahof - opened
Is there a step-by-step guide on how to fine-tune ASR on my own dataset?
+1
The tutorial is not adapted for the tokenizer specific to 1b-v2. I couldn’t figure how to setup the config file.
Any help would be highly appreciated !
Thanks
+1 looking for the same
+1 a tutorial to fine tune canary-1b-v2 would be greatly helpful!