Spencer Grimes 4cb0a78486 fix: squeeze audio to 1D before applying effects ...

The TTS model returns a 2D array [samples, 1], but librosa.effects
functions expect 1D arrays. This was causing the warning:
'n_fft=2048 is too large for input signal of length=1'

Fix: Squeeze to 1D before effects, reshape back after.

Also moved the effects application logic to handle the shape
conversion properly.

2026-01-31 16:50:43 -06:00

30 KiB

Raw Blame History

View Raw