"""Differentiable Feedback Delay Networks with Learnable Delay Lines.

A clean, open-source PyTorch implementation of:

    A. I. Mezza, R. Giampiccolo, E. De Sena, A. Bernardini,
    "Data-driven room acoustic modeling via differentiable feedback delay
    networks with learnable delay lines,"
    EURASIP Journal on Audio, Speech, and Music Processing, 2024(1):51.
    arXiv:2404.00082

An FDN is the classic Schroeder/Jot artificial-reverberation structure: a bank
of delay lines coupled by a feedback matrix. Here *every* parameter is made
differentiable -- crucially the delay-line lengths themselves -- so the whole
network can be fit to a measured Room Impulse Response (RIR) by backpropagation.
"""

from .fdn import DifferentiableFDN
from .losses import edc_loss, soft_edp_loss, edc, soft_edp, EDPConfig
from .train import fit_fdn, TrainConfig

__all__ = [
    "DifferentiableFDN",
    "edc_loss",
    "soft_edp_loss",
    "edc",
    "soft_edp",
    "EDPConfig",
    "fit_fdn",
    "TrainConfig",
]

__version__ = "0.1.0"