Cactus Compute's Whistle, a 16.9 MB speech-to-text model that runs on a CPU, was benchmarked against Whisper base. On LibriSpeech test-other it scored a 10.47% word error rate, 2.19 points better than greedy Whisper base, while beam search showed no gap. It ran 5.7 times faster on ten-second clips. https://www.marktechpost.com/2026/10/21/cactus-whistle-vs-whisper-base-speech-to-text-benchmark-cpu-guide/ #AIagent #AI #GenAI #AIresearch
MarkTechPostA Coding Guide to Cactus Whistle: Does a 16.9 MB Speech Model Hold Up Against Whisper Base? Word Error Rate, Speed, Streaming, Timestamps, Keywords, and Speech-to-Tool Calls on a CDiscover how Cactus Compute's 16.9 MB speech model compares to Whisper base on accuracy, speed, and CPU performance.