Profile-reward recipe: generate 640 (batched) → ASR-filter+trim → SIDON → keep the top 20% by a per-character quality+profile reward → warm-start FT 3 epochs. Below: the quality range of the selected training set, then example generations after each epoch.
trilliax
Characteristic dimensions (auto, from its own voice profile): ▲ GEND ▲ S_MONO ▲ S_STRY ▲ STRU ▼ S_RANT ▼ S_ASMR ▼ EXPL ▼ COGL · emo: Concentration Interest Emotional_Numbness
Training set = top-20% by reward = z(genu)+z(blend)+z(quality)−z(WER)+0.7·z(profile-match). Kept 128/640.
Best 5 of the kept top-20%
R 6.07 · genu 0.21 · blend 0.37 · qual 0.42 · WER 0.00
R 5.80 · genu 0.09 · blend 0.37 · qual 0.64 · WER 0.00
R 5.72 · genu 0.17 · blend 0.52 · qual 0.44 · WER 0.00
R 5.17 · genu 0.10 · blend 0.32 · qual 0.62 · WER 0.00
R 5.06 · genu 0.07 · blend 0.43 · qual 0.68 · WER 0.00
Weakest 5 still inside the top-20% (the selection boundary)
R 1.32 · genu 0.07 · blend 0.03 · qual 0.60 · WER 0.00
R 1.32 · genu 0.03 · blend 0.14 · qual 0.66 · WER 0.00
R 1.31 · genu 0.13 · blend 0.11 · qual 0.42 · WER 0.00
R 1.31 · genu 0.04 · blend 0.06 · qual 0.63 · WER 0.00
R 1.29 · genu 0.08 · blend 0.05 · qual 0.58 · WER 0.00
Fantasy line — refined ep1 / ep2 / ep3
“The old road winds past the ruined tower where the last dragon knights once kept their watch.”
Sci-fi line — refined ep1 / ep2 / ep3
“The station drifted in low orbit while the reactor cooled and the scanners swept the empty dark.”
Neutral line — refined ep1 / ep2 / ep3
“The meeting is scheduled for three o'clock and the report is on the desk by the printer.”