Views
No views yet
torch.onnx.export(dynamo=False)), so the model runs on the ONNX Runtime
DirectML EP (and every other EP).canary-1b-v2-onnx encoder is a torch-dynamo export. On the DirectML EP it is a two-sided
trap (isolated by graph bisection): dynamic shapes crash the Reshape/attention kernels
(MLOperatorAuthorImpl.cpp:2597, then a D3D12 device-removal 887A0020), and forcing static shapes
fails session creation in InferAndVerifyOutputSizes (:2853) — both unfixed ORT-DML defects around
the dynamo view idiom (upstream onnxruntime #26826 / #26944; the DML EP is in maintenance mode).
NVIDIA's Parakeet FastConformer, exported via TorchScript, runs fine on DML — so this repo re-exports
the same encoder the same way.encoder-model.onnx (+ encoder-model.int8.onnx): re-exported from the nvidia/canary-1b-v2 NeMo
checkpoint via torch.onnx.export(dynamo=False, opset=17), same I/O contract as istupakov
(audio_signal[B,128,T], length[B] → encoder_embeddings[B,S,1024], encoder_mask[B,S]).
Numerically identical to istupakov's encoder on CPU (max|Δ| ≈ 4e-6 — export-tracer float noise).decoder-model.onnx / decoder-model.int8.onnx / config.json / vocab.txt: unchanged from
istupakov/canary-1b-v2-onnx — the DML crash was
encoder-only; the AED decoder is byte-for-byte the same.canary_encoder_export.py.