News for hackers. Stuff that matters.

A comment on Silero V3: fast high-quality text-to-speech in 20 languages with 173 voices. Parent comment

Re:Silero V3: fast high-quality text-to-speech in 20 languag... by snakers41 on Monday June 20, 2022 @10:26AM (#31810730)
For STT models - yes. For TTS models - not yet.
[ Parent | on HN ]
Re:Silero V3: fast high-quality text-to-speech in 20 languag... by rurounijones on Monday June 20, 2022 @07:51PM (#31817829)
Awesome. Is there an active plan to make the TTS models available on ONNX? Or is it something that is possible but is not being worked on right now? Is there an issue / ticket somewhere that I can follow (Or should I create one?)
[ Parent | on HN ]
Re:Silero V3: fast high-quality text-to-speech in 20 languag... by snakers41 on Monday June 20, 2022 @09:18PM (#31818576)
It is possible, albeit with a significant simplification of the capabilities of the models (i.e. all of the SSML stuff will be left out).

Also ONNX boasts native quantization that just works.

But we are not currently actively working on this. Most likely ONNX will only be available only for commercial customers for special buds, but we are not decided on this yet.

[ Parent | on HN ]