How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

KV-cache / low-latency decoding for custom fine-tuned Whisper on Hailo-10H?

calendar_today November 13, 2026 person @John_Doe2 domain hailo

Thanks for this — it is the only public report I can find of a custom fine-tune running on a 10H, and we are trying to do the same thing and cannot get past the parser. We have a Whisper-Small fine-tuned on custom audio segments, exported with the same hailo-whisper toolkit (patched fork, opset 13, 10 s window, 48-token decode). ClientRunner(hw_arch=”hailo10h”).translate_onnx_model() fails on the encoder, for both small and tiny, identically on DFC 5.1.0, 5.2.0, 5.3.0 and 5.4.0: Invalid kernel shape for base conv layer base_conv3 (translated from MatMul_2).

open_in_new Read original post