Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

nvidia
/
canary-1b-flash

Automatic Speech Recognition
NeMo
Safetensors
PyTorch
fastconformer
automatic-speech-translation
speech
audio
Transformer
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Model card Files Files and versions
xet
Community
16

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
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Add Open ASR Leaderboard evaluation results

#16 opened about 2 months ago by
SaylorTwift

colab notebooks do not work

2
#15 opened 5 months ago by
malinphy

Looks like someone has made a webui utilizing canary already

👍 1
#13 opened 9 months ago by
methinkss

add AIBOM

#11 opened 11 months ago by
sabato-nocera

The results are incorrect, with words missing, after implementing the timestamps.

2
#10 opened about 1 year ago by
will1130

RTF evaluation issues

3
#9 opened about 1 year ago by
cX1y

Punctuation and Timestamps?

4
#8 opened about 1 year ago by
eek

Japanese?

❤️ 2
2
#6 opened about 1 year ago by
riken12

Error with Canary Model: "Computing timestamps are not supported for this model yet"

2
#5 opened about 1 year ago by
nourlab

Thanks to NVIDIA who released Canary-1B-Flash speech recognition under the Free Software license!

❤️ 1
#4 opened about 1 year ago by
JLouisBiz
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs