Do you have any accuracy benchmarks?
I’ve worked in this space. TTS in a small footprint isn’t the hard part —- it’s doing it accurately that’s hard.
Although for the use cases OP is targeting, lower accuracy may be good enough!
Speech Recognition and TTS in less than 500kb
11–20 of 101 posts
Re: Speech Recognition and TTS in less than 500kb
#12It looks great, thank you! I'll see if I can use it for my in browser AI assistant project's ( https://aidekin.com ) voice part. It's currently using Nemotron-3.5-ASR and supertonic-3 but overall it requires 1.2gb download.
Re: Speech Recognition and TTS in less than 500kb
#13Do you have any accuracy benchmarks? I’ve worked in this space. TTS in a small footprint isn’t the hard part —- it’s doing it accurately that’s hard. Although for the use cases OP is targeting, lower accuracy may be good enough!
> I’ve worked in this space. TTS in a small footprint isn’t the hard part —- it’s doing it accurately that’s hard.
This actually holds for everything in AI.
Re: Speech Recognition and TTS in less than 500kb
#14Do you have any accuracy benchmarks? I’ve worked in this space. TTS in a small footprint isn’t the hard part —- it’s doing it accurately that’s hard. Although for the use cases OP is targeting, lower accuracy may be good enough!
If you look at this chart here it seems the tiny model has a WER of ~12%… not sure about the micro model:
https://github.com/moonshine-ai/moonshine#when-should-you-ch...
Re: Speech Recognition and TTS in less than 500kb
#15I installed the command line version using uv
uv init
uv add moonshine-voice
uv run moonshine-voice mic --language en
good job on a clear readme.md tbh
Re: Speech Recognition and TTS in less than 500kb
#16Very cool. I've done TTS on a 32K Arduino but it was pretty croaky. https://youtu.be/ErGDboTpwM0
Re: Speech Recognition and TTS in less than 500kb
#17I installed the command line version using uv uv init uv add moonshine-voice uv run moonshine-voice mic --language en super nice to be able to run it to test it like this good job on a clear readme.md tbh
`uvx moonshine-voice mic --language en` That is even simpler.
Re: Speech Recognition and TTS in less than 500kb
#18Do you have any accuracy benchmarks? I’ve worked in this space. TTS in a small footprint isn’t the hard part —- it’s doing it accurately that’s hard. Although for the use cases OP is targeting, lower accuracy may be good enough!
If you look at this chart here it seems the tiny model has a WER of ~12%… not sure about the micro model: https://github.com/moonshine-ai/moonshine#when-should-you-ch...
That's the error rate for STT, not TTS. TTS is generally easier than STT because you only need to produce one valid pronunciation and don't need to handle variation within and between individuals.
Re: Speech Recognition and TTS in less than 500kb
#19For TTS I wonder how this compares to nanotts[1] with the en-GB voice, which is sort of unreasonably good.
Re: Speech Recognition and TTS in less than 500kb
#20this is good to see. i also trained a stt under 500kb for sub dollar chips. it had about 20 words that it could understand(like start, stop, left, right, go, up etc) and then the spell mode where you could say the word spell and then say the individual english alphabets and close with spell. it was super fun to work on. these tend to be extremely unstable though, like confusion between p and t (at least for my accent). will have to try this one now.