Automatic Speech Recognition
NeMo
ONNX
GGUF
parakeet
tdt
sherpa-onnx
multilingual
speech-recognition
gabor
fastconformer
Instructions to use aoiandroid/orukeet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use aoiandroid/orukeet with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("aoiandroid/orukeet") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
|
Download report/assets/kernel-fits-caption.md from aoiandroid/orukeet: direct link, hf CLI and curl.
- Browser
- Download file 345 Bytes
-
https://huggingface.co/aoiandroid/orukeet/resolve/main/report/assets/kernel-fits-caption.md
- Command line
-
hf download hf://aoiandroid/orukeet/report/assets/kernel-fits-caption.md
-
curl -L -o kernel-fits-caption.md https://huggingface.co/aoiandroid/orukeet/resolve/main/report/assets/kernel-fits-caption.md
345 Bytes
Four exact kernel replacements. Examples are ranks 1,537, 4,609, 7,680 and 10,752 of the selected 12,288, nearest the 12.5th, 37.5th, 62.5th and 87.5th fit-error percentiles. Each pair is divided by the original kernel L2 norm. Markers are the nine stored taps; connecting lines guide the eye. RMS percentages are relative to the original norm.