vae.ckpt is a full training checkpoint containing discriminator, STFT
loss modules, and EMA wrappers that are absent from the inference
AudioAutoencoder. strict=False ignores these training-only keys while
still loading all encoder/decoder/bottleneck weights correctly.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
PrismAudioFeatureExtractor now creates and populates a managed venv
(_extract_env/) automatically when python_env is left as the default
'python'. Also adds scripts/install_extract_env.sh for manual/Docker
setup without conda.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Ethanfel