CPU vs GPU Decoding for Low‑Traffic Kaldi Workloads: Cost Trade‑off
Goal Minimise total hosting cost while maintaining acceptable ASR accuracy for a sporadic, low‑traffic workload. Constraints & Uncertainty GPU instances carry a fixed hourly charge that is wasted when traffic is idle, whereas CPU decoding scales linearly with the number of active requests. Compact nnet3 chain models reduce CPU load but may degrade WER, e
kaldi