Automatic Speech Recognition
NeMo
English
speech
audio
NeMo
parakeet
TDT
FastConformer
quantization
binary
1-bit
quantization-aware-training
knowledge-distillation
Eval Results (legacy)
Instructions to use rajb3/kea-b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use rajb3/kea-b with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("rajb3/kea-b") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Commit History
13 days ago
-
Model card: add the research runtime's speed and energy at a glance; add RUNTIME.md (#1)
- Model card: add the research runtime's speed and energy at a glance; add RUNTIME.md (4d9f18b4b1a6fb494f88e71017842f89d9193f9d)cfb1353
14 days ago
-
Kea-B: 1-bit Parakeet-TDT-0.6B-v2 (MB1 final export)
Verified signature5e7c298 -
initial commit
Verified signatured95e3fd