Re:Coqui.ai TTS: A Deep Learning Toolkit for Text-to-Speech
by eginhard on Tuesday June 11, 2024 @02:34PM
(#40649816)
They just shared the paper for XTTS, which got accepted to Interspeech and might be the reason for this being posted now: https://arxiv.org/abs/2406.04904
Re:Coqui.ai TTS: A Deep Learning Toolkit for Text-to-Speech
by jsemrau on Tuesday June 11, 2024 @03:39PM
(#40650574)
Interesting. I got quite good results for my longform substack by combining xTTS2 with Nvidia's Nemo.
Re:Coqui.ai TTS: A Deep Learning Toolkit for Text-to-Speech
by WhitneyLand on Tuesday June 11, 2024 @05:39PM
(#40651882)
Anyone have a sense for how these compare to OpenAI’s TTS?
Re:Coqui.ai TTS: A Deep Learning Toolkit for Text-to-Speech
by jonahx on Tuesday June 11, 2024 @09:25PM
(#40653544)
Somewhat unrelated, but given that anyone can vote anonymously, how is the TTS-Arena protecting itself against bots or even rings of humans gaming the system?
Re:Coqui.ai TTS: A Deep Learning Toolkit for Text-to-Speech
by modeless on Tuesday June 11, 2024 @10:09PM
(#40653784)
Low stakes, I guess
Re:Coqui.ai TTS: A Deep Learning Toolkit for Text-to-Speech
by Grimblewald on Wednesday June 12, 2024 @02:06AM
(#40655044)
problem is that low stakes divided by low cost of bots is still an acceptable return.
Personally I prefer StyleTTS 2, and it has a better license. But XTTSv2 has a streaming mode with pretty low latency which is nice. I did run into hallucination issues though. It will hallucinate nonsense words or insert extra syllables in words, pretty frequently.
As others mentioned they shut down so there won't be any updates to XTTS.