News for hackers. Stuff that matters.
Re:Sopro TTS: A 169M model with zero-shot voice cloning that... by woodson on Thursday January 08, 2026 @05:36PM (#46547488)
Does the 169M include the ~90M params for the Mimi codec? Interesting approach using FiLM for speaker conditioning.
Re:Sopro TTS: A 169M model with zero-shot voice cloning that... by sammyyyyyyy on Thursday January 08, 2026 @05:52PM (#46547668)
No, it doesn’t.