You will have created the first of its kind, and you’ll be famous! If you can create a completely open source wake implementation that gets even remotely close to the performance and reliability of those from Espressif, etc (while running on a microcontroller) we would be thrilled to use it.
Yes, in the 15 seconds it took you to write that comment you came up with something no one in the field has ever thought of before. It’s getting very, very old and I’ve all but given up engaging on it because it always ends with the classic “Well couldn’t you just…”. Everyone has an opinion and exactly zero of them have any idea what they are talking about (that I’ve encountered). That said, wake word comes up more than I could have ever imagined. Someone else linked to the Espressif training dataset requirements. Yet it requires a not-completely dissimilar level of effort. You’re not going to see OpenAI, Meta, etc release a microcontroller optimized wake implementation because literally no one cares (by comparison). This isn’t Whisper or an LLM that has applications in practically anything. Short answer: it’s a tiny niche that is still very difficult, expensive, and time consuming.
0 kommentar(er)
