sherpa-onnx nemo parakeet-unified streaming 560ms — fp16 ONNX
fp16 conversion of csukuangfj2/sherpa-onnx-nemo-parakeet-unified-en-0.6b-streaming-560ms
(buffered/unified streaming export; same layout, .fp16 suffix), via onnxruntime's
transformers.float16 converter (keep_io_types=True). Transcripts verified identical to fp32
end-to-end on DirectML; half the download/VRAM. Made for WinSTT.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Masterx/sherpa-onnx-nemo-parakeet-unified-en-0.6b-streaming-560ms-fp16
Base model
nvidia/parakeet-unified-en-0.6b