[dead]
Show HN: Three new Kitten TTS models – smallest less than 25MB
81–90 of 201 posts
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#82A lot of good small TTS models in recent times. Most seem to struggle hard on prosody though. Kokoro TTS for example has a very good Norwegian voice but the rhythm and emphasizing is often so out of whack the generated speech is almost incomprehensible. Haven't had time to check this model out yet, how does it fare here? What's needed to improve the models in this area now that the voice part is more or less solved?
small models struggle with prosody due to limited capacity. this version does much better than the precious one and is the best among other <25MB models. Kokoro is a really good model for its size, its competitive on artificial analysis too. i think by the next release we should have something kokoro quality but a fifth of the size. Adding control for rhythm seems to be quite important too, and we should start lookin…
Listened to the video examples, sounded very good though wasn't terribly challenging text.
If only I could have that in Norwegian my SO would be pleased.
Also I totally misremembered regarding Kokoro TTS. It's good, but not what was butchering Norwegian. Forgot which one I was thinking of, maybe it was the old VITS stuff Rhaspy uses. Points stand, the voice was good but could barely understand what was said.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#83Was playing around a bit and for its size it's very impressive. Just has issues pronounciating numbers. I tried to let it generate "Startup finished in 135 ms."
I didn't expect it to pronounciate 'ms' correctly, but the number sounded just like noise. Eventually I got an acceptable result for the string "Startup finished in one hundred and thirty five seconds.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#84sounds amazing! does it stream? or is it so fast you don't need to?
it can support chunk streaming, i'm working on adding it to the repo. should be up by tomorrow.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#85Wow, what an amazing feat. Congratulations!
thank you so much. glad you liked the model.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#86Great stuff. Is your team interested in the STT problem?
Yes, we've started working on it and will have a range of stt models v soon. lmk if you have a prod use-case in mind?
From my point of view, Parakeet is not very good at formatting the output, so it would be nice if a small model focused on having nicely formatted (and correct) text, not just the lowest WER score. Rewarding the model for inserting logical line breaks, quotation marks, etc.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#87I ran install instructions and it took 7.1GB of deps, tf you mean "tiny" ?
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#88I ran install instructions and it took 7.1GB of deps, tf you mean "tiny" ?
damnn, lemme fix it, sorry for that. we may have forgotten to remove the redundant dependencies. i'll comment here once i push the change. thanks a lot for trying it and giving feedback.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#89What's the actual install size for a working example? Like similar "tiny" projects, do these models actually require installing 1GB+ of dependencies?
Running the example is 3 MiB for the repo, +667 MiB of Python dependencies, +86 MiB of models that will get downloaded from HuggingFace. =756 MiB. (That's using the example as-is. If you switch it to the smaller model, modify the above with +57 MiB of models from HuggingFace, or =727 MiB.) So I toyed with this a bit + the Rust library "ort", and ort is only 224M in release (non-debug) mode, and it was pretty simple t…
So, that was on macOS. It's actually huge on Linux, and I've run out of disk space trying to pull dependencies. It's nvidia, who always shows great judgement in their use of disk.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#90Was playing around a bit and for its size it's very impressive. Just has issues pronounciating numbers. I tried to let it generate "Startup finished in 135 ms." I didn't expect it to pronounciate 'ms' correctly, but the number sounded just like noise. Eventually I got an acceptable result for the string "Startup finished in one hundred and thirty five seconds.
yeah we're fixing this at the model level too. but in the meantime, there is a way to add text preprocessing for you, and if you have a special use-cased, claude code should be able to one-shot custom preprocessing. its the way that most existing tts models (including sota cloud ones) deal w numbers and units, they just convert it into string.