AudioSR2023music
High-Frequency Restoration - AudioSR (AudioSR)
Model card for the AudioSR model behind the High-Frequency Restoration - AudioSR preset in Neural Analog.
2x
Available in Studio. Consumes 2x the processing minutes.
AudioSR Description
This model regenerates high frequencies above the selected cutoff and keeps the original audio below it. The lower the cutoff, the more of the sound it reconstructs. Great for historical recordings, poor-quality recordings, or recordings with unwanted high-frequency noise. It does not change the bass (use an AI cover model instead).
AudioSR Architecture
AudioSR Parameters
| Key | Label | Options | Description |
|---|---|---|---|
| frequency_cutoff | Strength | Very Subtle (16 kHz cutoff) (16000), Subtle (13 kHz cutoff) (13000), Mild (10 kHz cutoff) (10000), Medium (8 kHz cutoff) (8000), Pronounced (5 kHz cutoff) (5000), Strong (4 kHz cutoff) (4000), Very Strong (3 kHz cutoff) (3000) | Sets the frequency above which AudioSR regenerates the high end. A low cutoff reconstructs more of the frequency spectrum. A high cutoff focuses on the highest frequencies (which are less audible). |
| reconstruction_method | Reconstruction | Multiband Ensemble (multiband_ensemble), Continuous Reconstruction (original_signal) | No additional help text. |
| stereo_mode | Channels | Stereo (Mid/Sides) (mid_sides), Sides only (sides_only), Mid only (mid_only), Stereo (L/R) (left_right), Mono (mono) | No additional help text. |