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-180m-flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/canary-180m-flash with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/canary-180m-flash") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Add Open ASR Leaderboard evaluation results
#10 opened about 1 month ago
by
SaylorTwift
Cannot use the model on language other than Englih
#9 opened about 2 months ago
by
dudewiththenose
Finetune for new language
#8 opened 4 months ago
by
teeofftechnologies
finetune the decoder on text only data?
1
#7 opened 10 months ago
by
leestevennz
Processing dataset?
6
#6 opened about 1 year ago
by
Nguyen667201
Computing timestamps are not supported for canary_model?
🔥😎 2
5
#5 opened about 1 year ago
by
Nguyen667201
Finetuning guide? Supported audio formats while finetuning?
5
#4 opened about 1 year ago
by
neurlang