Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Three new Kitten TTS models – smallest less than 25MB

github.com

Post reply on HN
Print view View original

121–130 of 201 posts

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#121

Post by meatmanek »

_hzw wrote: post #104

I'd love to see a monolingual Japanese model sometime in the future. Qwen3-tts works for Japanese in general, but from time to time it will mix with some Mandarin in between, making it unusable.

You could try a preprocessing step where you convert to hiragana, but I guess that would lose pitch accent information (e.g. 飴 vs 雨)

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#122

Post by Aerroon »

RobertoG wrote: post #111
Aerroon wrote: post #107

Earlier quoted context omitted.

I'm jealous. It took me far longer and much more frustration to get it to run. Had to get the right Python version and make sure it didn't break anything with the previous Python version. A friend suggested using Docker, so I started down that path until I realized I'd probably have to set the whole thing up there myself. Eventually got it to run and I think I didn't break anything else. I hate Python so much.

why you don't use some kind of environment, Conda or something like that?

Because I need a new version of python very rarely (years go by). I don't remember all the arcane incantations to set everything up.

I did eventually do that though, and I'm pretty sure I had to mess about with installing and uninstalling torch.

I dread using anything made in python because of this. It's always annoying and never just works (if the version of python is incompatible, otherwise it's fine) .

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#123

Post by deathanatos »

RobertoG wrote: post #111
Aerroon wrote: post #107

Earlier quoted context omitted.

I'm jealous. It took me far longer and much more frustration to get it to run. Had to get the right Python version and make sure it didn't break anything with the previous Python version. A friend suggested using Docker, so I started down that path until I realized I'd probably have to set the whole thing up there myself. Eventually got it to run and I think I didn't break anything else. I hate Python so much.

why you don't use some kind of environment, Conda or something like that?

I used uv, which should have generated a stable environment. No dice. There's a bug in spacey.

I suspect success is highly variable on macOS vs. Linux; the spacey bug is only in newer (3.14 only or later) Pythons, which Linux will have.

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#124

Post by _hzw »

meatmanek wrote: post #121
_hzw wrote: post #104

I'd love to see a monolingual Japanese model sometime in the future. Qwen3-tts works for Japanese in general, but from time to time it will mix with some Mandarin in between, making it unusable.

You could try a preprocessing step where you convert to hiragana, but I guess that would lose pitch accent information (e.g. 飴 vs 雨)

Exactly. Qwen only has one pitch accent for pure hiragana words, even though it actually work (removing mandarin mixed-in), which requires some great efforts to normalize text in order to disambiguate heteronyms, the result is (if you use voice cloning) your favorite CV speaking in some weird, unknown accent :)

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#125

Post by jacquesm »

RobertoG wrote: post #111
Aerroon wrote: post #107

Earlier quoted context omitted.

I'm jealous. It took me far longer and much more frustration to get it to run. Had to get the right Python version and make sure it didn't break anything with the previous Python version. A friend suggested using Docker, so I started down that path until I realized I'd probably have to set the whole thing up there myself. Eventually got it to run and I think I didn't break anything else. I hate Python so much.

why you don't use some kind of environment, Conda or something like that?

Conda was fantastic up to some point last year and since then I've had quite a few unresolvable version issues with it. It is really annoying, especially when you're tying multiple things together and each requires its own set of mutually exclusive specific versions of libraries. The latest like that was gnu radio and some out-of-tree stuff at the same time as a bluetooth library. High drama. I eventually gave up, rewrote the whole thing in a different language and it took less time than I had spent on trying to get the python solution duct-taped together.

I should learn to give up quicker.

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#129

Post by stavros »

Aerroon wrote: post #107
kevin42 wrote: post #6

What I love about OpenClaw is that I was able to send it a message on Discord with just this github URL and it started sending me voice messages using it within a few minutes. It also gave me a bunch of different benchmarks and sample audio. I'm impressed with the quality given the size. I don't love the voices, but it's not bad. Running on an intel 9700 CPU, it's about 1.5x realtime using the 80M model. It wasn't an…

I'm jealous. It took me far longer and much more frustration to get it to run. Had to get the right Python version and make sure it didn't break anything with the previous Python version. A friend suggested using Docker, so I started down that path until I realized I'd probably have to set the whole thing up there myself. Eventually got it to run and I think I didn't break anything else. I hate Python so much.

Nowadays these frustrations shouldn't be a thing any more. If the author used uv, the script would be able to install its own dependencies and just work.
Post reply on HN