"""ECAPA-TDNN Speaker Encoder configuration.

Standalone configuration for the ECAPA-TDNN speaker encoder extracted from
Qwen3-TTS. Compatible with the HuggingFace transformers AutoModel API.
"""

from transformers import PretrainedConfig


class EcapaTdnnSpeakerEncoderConfig(PretrainedConfig):
    r"""
    Configuration class for the ECAPA-TDNN speaker encoder.

    This model produces fixed-dimensional speaker embeddings (x-vectors) from
    log-mel spectrograms. The architecture follows the ECAPA-TDNN paper:
    "Emphasized Channel Attention, Propagation and Aggregation in TDNN Based
    Speaker Verification" (https://arxiv.org/abs/2005.07143).

    Args:
        mel_dim (`int`, *optional*, defaults to 128):
            Number of mel-frequency bins in the input spectrogram.
        enc_dim (`int`, *optional*, defaults to 1024):
            Dimension of the output speaker embedding.
        enc_channels (`list[int]`, *optional*, defaults to `[512, 512, 512, 512, 1536]`):
            Output channels for each encoder layer. The first is the initial
            TDNN layer, the middle ones are SE-Res2Net blocks, and the last is
            the multi-layer feature aggregation layer.
        enc_kernel_sizes (`list[int]`, *optional*, defaults to `[5, 3, 3, 3, 1]`):
            Kernel sizes for each encoder layer.
        enc_dilations (`list[int]`, *optional*, defaults to `[1, 2, 3, 4, 1]`):
            Dilation rates for each encoder layer.
        enc_attention_channels (`int`, *optional*, defaults to 128):
            Number of attention channels in the attentive statistics pooling layer.
        enc_res2net_scale (`int`, *optional*, defaults to 8):
            Scale factor for the Res2Net blocks.
        enc_se_channels (`int`, *optional*, defaults to 128):
            Number of channels in the squeeze-excitation bottleneck.
        sample_rate (`int`, *optional*, defaults to 24000):
            Expected audio sample rate in Hz.
    """

    model_type = "ecapa_tdnn_speaker_encoder"

    def __init__(
        self,
        mel_dim=128,
        enc_dim=1024,
        enc_channels=None,
        enc_kernel_sizes=None,
        enc_dilations=None,
        enc_attention_channels=128,
        enc_res2net_scale=8,
        enc_se_channels=128,
        sample_rate=24000,
        **kwargs,
    ):
        super().__init__(**kwargs)
        self.mel_dim = mel_dim
        self.enc_dim = enc_dim
        self.enc_channels = enc_channels if enc_channels is not None else [512, 512, 512, 512, 1536]
        self.enc_kernel_sizes = enc_kernel_sizes if enc_kernel_sizes is not None else [5, 3, 3, 3, 1]
        self.enc_dilations = enc_dilations if enc_dilations is not None else [1, 2, 3, 4, 1]
        self.enc_attention_channels = enc_attention_channels
        self.enc_res2net_scale = enc_res2net_scale
        self.enc_se_channels = enc_se_channels
        self.sample_rate = sample_rate