From the source
Hume introduced a leaderboard that evaluates how well text-to-speech models follow directions, finding that some models do not change their output regardless of the instruction given.
From the source
From the source
Leaderboard tests TTS model instruction following
![Blog Image [whisper] Tag Applied](/api/post-media/b4e461f066eed5ac7cc0fa248c0bc0006f088fe67b376ca305a8b5839aede0d2.jpg)
From the source
New leaderboard tests whether text-to-speech models actually follow direction, finding that for some models the dial doesn't move no matter what you ask.
hume.ai