| ▲ | Rebuilding my local voice assistant pipeline(blog.platypush.tech) | ||||||||||||||||
| 54 points by todsacerdoti 4 hours ago | 11 comments | |||||||||||||||||
| ▲ | mewse-hn an hour ago | parent | next [-] | ||||||||||||||||
Interesting write up, I've been vibe coding an android voice assistant using a similar pipeline without a wakeword - VAD > ASR > LLM > TTS 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 | |||||||||||||||||
| |||||||||||||||||
| ▲ | mmmooo an hour ago | parent | prev | next [-] | ||||||||||||||||
older amazon echo dots and shows really make great hardware for this, combined with homeassistant, and can be had for very little cost. e.g. shameless plug: https://github.com/ygelfand/echolocal | |||||||||||||||||
| |||||||||||||||||
| ▲ | fragilerock 3 hours ago | parent | prev | next [-] | ||||||||||||||||
Interesting read! I have my own local voice assistant and I implemented exactly the same question mark trick just the other day. 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. | |||||||||||||||||
| ▲ | dofm an hour ago | parent | prev | next [-] | ||||||||||||||||
Just what I want to read — favourited to come back to! | |||||||||||||||||
| ▲ | bityard an hour ago | parent | prev | next [-] | ||||||||||||||||
Is this complimentary to, or an alternative to Home Assistant? | |||||||||||||||||
| |||||||||||||||||
| ▲ | stavros 3 hours ago | parent | prev [-] | ||||||||||||||||
This is really useful, thanks! The other day I bought a small screen and didn't know what to do with it so I made an assistant that talks to my bot: 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. | |||||||||||||||||