105 points by todsacerdoti about 12 hours ago | 16 comments | View on ycombinator
mmmooo about 8 hours ago |
mewse-hn about 8 hours ago |
I've found parakeet to be much, much better than whisper and I made a 4 bit quant of parakeet 110M for my crappier android test devices, it would probably fit a raspberry pi:
https://huggingface.co/mewse/parakeet-tdt_ctc-110m-onnx-int4
bill10 about 3 hours ago |
fragilerock about 10 hours ago |
The overall pipeline is quite similar to my previous setup, but I found the STT -> LLM -> TTS pipeline just infuriatingly slow. TTS and STT with whisper/piper worked fine and reasonably fast for me locally, but the real bottleneck was always the fact that they're not running concurrently with the LLM call. I ended up forking an open source openai realtime API ESP32 plugin and patching it to my liking. It's a bit more expensive in terms of API cost but I only use it sparingly and it's so much nicer to use now.
bityard about 8 hours ago |
dofm about 8 hours ago |
stavros about 11 hours ago |
https://m.youtube.com/shorts/3FseVyAG5uM
I used microwakeword too, and training my own wakeword was pretty simple (basically just recording a few tens of samples). Highly recommended.
I also wanted to be able to issue some voice commands for lights and other things in my home with low latency, so I added a short-circuit plugin that runs right after recognition. If the recognized command matches one of the regexes, it's immediately executed, which has a latency of under a second. Otherwise, it gets sent to my assistant, which usually will tweak the regex (or add a new one) to improve the whole system as it fails.
yuvicodesk17 44 minutes ago |
meatbal_mike about 10 hours ago |
cgg7709 about 10 hours ago |
allentown521 about 5 hours ago |