This was fantastic! How many samples were thrown at the mics? Would be great to know what baseline WER was if audio was fed directly to the API. Benchmarking is critical for knowing which technology will actually perform best. One thing we’ve seen from our experience is that linear array mics (e.g. PS3 Eye) tend to perform better than circular arrays when the angle of arrival is known and within 180 degrees. Would love to see more of this!