ONNX
Open model interchange format
Episodes
-
#6222: Why Fine-Tuning Runs Can't Always ResumeEighty cents and twenty-five minutes per training run — so why does the checkpoint question still keep a tinkerer up at night? -
#5805: Freeze the Model, Move the LabelsYour classifier isn't stale — your label set moved. Why retraining is cheap, and why not retraining might be smarter. -
#5460: Four Small Models, One Android Phone: Does It Actually Work?A chained on-device dictation pipeline — VAD, ASR, cleanup — and why "it feels smooth" isn't the same as knowing it works. -
#1544: Why It Costs More to Run AI Than to Build ItDiscover why the AI runtime is the unsung hero of the tech stack, determining whether your AI feels like a snappy conversation or a slow crawl. -
#3: Safetensors or something else: STT inference formats explainedUnpacking ASR weight formats: Safetensors and beyond. Tune in to understand the distinctions.