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.
guttural-imp
Characteristic dimensions (auto, from its own voice profile): ▲ S_STRY ▲ S_MONO ▲ CLRT ▲ S_CASU ▼ S_RANT ▼ EXPL ▼ S_NEWS ▼ COGL · emo: Concentration Interest Awe
Training set = top-20% by reward = z(genu)+z(blend)+z(quality)−z(WER)+0.7·z(profile-match). Kept 127/638.
Best 5 of the kept top-20%
R 5.44 · genu 0.20 · blend 0.55 · qual 0.42 · WER 0.00
R 5.34 · genu 0.17 · blend 0.22 · qual 0.72 · WER 0.00
R 5.34 · genu 0.20 · blend 0.47 · qual 0.58 · WER 0.00
R 5.25 · genu 0.18 · blend 0.35 · qual 0.57 · WER 0.00
R 5.00 · genu 0.17 · blend 0.32 · qual 0.56 · WER 0.00
Weakest 5 still inside the top-20% (the selection boundary)
R 1.41 · genu 0.12 · blend 0.01 · qual 0.64 · WER 0.00
R 1.40 · genu 0.11 · blend 0.06 · qual 0.60 · WER 0.03
R 1.38 · genu 0.07 · blend 0.03 · qual 0.63 · WER 0.00
R 1.38 · genu 0.09 · blend 0.14 · qual 0.50 · WER 0.00
R 1.37 · genu 0.13 · blend 0.10 · qual 0.45 · 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.”