|
| ▲ | hexaga 2 hours ago | parent | next [-] |
| Kokoro is fine tunable? Speaking as someone who went down the rabbit hole... it's really not. There's no (as of last time I checked) training code available so you need to reverse engineer everything. Beyond that the model is not good at doing voices outside the existing voicepacks: simply put, it isn't a foundation model trained on internet scale data. It is made from a relatively small set of focused, synthetic voice data. So, a very narrow distribution to work with. Going OOD immediately tanks perceptual quality. There's a bunch of inference stuff though, which is cool I guess. And it really is a quite nice little model in its niche. But let's not pretend there aren't huge tradeoffs in the design: synthetic data, phonemization, lack of train code, sharp boundary effects, etc. |
|
| ▲ | jamilton 7 hours ago | parent | prev | next [-] |
| Being able to voice clone with PocketTTS seems major, it doesn't look like there's any support for that with Kokoro. |
| |
| ▲ | echelon 6 hours ago | parent [-] | | Zero shot voice clones have never been very good. Fine tuned models hit natural speaker similarity and prosody in a way zero shot models can't emulate. If it were a big model and was trained on a diverse set of speakers and could remember how to replicate them all, then zero shot is a potentially bigger deal. But this is a tiny model. I'll try out the zero shot functionality of Pocket TTS and report back. |
|
|
| ▲ | jhatemyjob 5 hours ago | parent | prev [-] |
| Less licensing headache, it seems. Kokoro says its Apache licensed. But it has eSpeak-NG as a dependency, which is GPL, which brings into question whether or not Kokoro is actually GPL. PocketTTS doesn't have eSpeak-NG as a dependency so you don't need to worry about all that BS. Btw, I would love to hear from someone (who knows what they're talking about) to clear this up for me. Dealing with potential GPL contamination is a nightmare. |
| |
| ▲ | miki123211 2 hours ago | parent [-] | | Kokoro only uses Espeak for text-to-phoneme (AKA G2P) conversion. If you could find another compatible converter, you could probably replace eSpeak with it. The data could be a bit OOD, so you may need to fiddle with it, but it should work. Because the GPL is outdated and doesn't really consider modern gen AI, what you could also do is to generate a bunch of text-to-phoneme pairs with Espeak and train your own transformer on them,. This would free you from the GPL license completely, and the task is easy enough that even a very small model should be able to do it. |
|
