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
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