wav2letter

Sure, that's probably the VAD, which can be tuned (the VAD decides if your phrase is done or not yet). That's part of why I included activity monitor watching w2l, so you could see it wasn't using any CPU while I talked. Would probably be more convincing if I printed something at the moment the VAD cut off the user so you could visually judge from the boundary of what we considered their speech. This video can be partially reproduced with the code and models from here: https://github.com/facebookresearch/wav2letter/issues/327 but most of our decoder optimizations post-date when I compiled that demo. Some of the later code is here: https://github.com/talonvoice/wav2letter/tree/w2lapi_static https://github.com/ckamm/wav2letter/tree/wip-parallel Here is the exact timing loop code I used in that demo: https://bochs.info/p/nhz5cv

I made a realtime mac demo of the acoustic model part of wav2letter++ including several trained models: https://github.com/facebookresearch/wav2letter/issues/327 Someone in that thread ported it to linux. This demo is just "acoustic model emissions", which are character level predictions (with no repeated characters), but I have "decoding" (turning into english sentences) working locally as well and I'll post a new demo at some point.

Obviously the big cloud players offer their own APIs and SDKs (for a price), but there are a few other solutions worth looking at. Facebook has open sourced some pre-trained models: https://github.com/facebookresearch/wav2letter Picovoice has some smaller, more efficient models capable of running on edge devices: https://github.com/Picovoice Full ASR does require quite large models and datasets, but you don't need nearly that much power or data to fine-tune a model for your own domain.

I developed chronic hand pain a couple of years ago (probably from overworking), so I quit my job and I've been making Talon [1] since, with the goal of making it possible for anyone to efficiently do anything/everything on their computer (general use, programming, games, niche apps) without their hands. Most recently I've been training acoustic models and writing a user frontend for the wav2letter++ [2] speech recognition engine, and porting Talon from Mac to cross-platform. [1] https://talonvoice.com [2] https://github.com/facebookresearch/wav2letter