from transformers import PretrainedConfig
from typing import List



class MeralionBestRqConformerEncoderConfig(PretrainedConfig):
    model_type = "meralion_bestrq"

    def __init__(
        self,
        input_dim: int = 80,
        input_channels: int = 1,
        num_attention_heads: int = 8,
        hidden_size: int = 1024, #embed_dim
        ffn_dim: int = 4096,
        num_hidden_layers: int = 24,
        conv_depthwise_kernel_size: int = 5,
        feat_proj_dropout: float = 0., #for input_projection
        activation_dropout: float = 0.,
        hidden_dropout: float = 0.,
        max_source_positions: int = 3000,
        no_scale_embedding: bool = False,
        hidden_act: str = "swish",
        conformer_conv_dropout: float = 0.,
        position_embeddings_type: str = "relative",
        attention_dropout: float = 0.,
        rotary_embedding_base: int = 10000,
        layerdrop = 0.,
        final_dropout = 0., #ctc
        vocab_size = None, #ctc
        ctc_loss_reduction = 'sum', #ctc
        ctc_zero_infinity = False, #ctc
        **kwargs,
    ):

        self.input_dim = input_dim
        self.input_channels = input_channels
        self.num_attention_heads = num_attention_heads
        self.hidden_size = hidden_size
        self.ffn_dim = ffn_dim
        self.num_hidden_layers = num_hidden_layers
        self.conv_depthwise_kernel_size = conv_depthwise_kernel_size
        self.feat_proj_dropout = feat_proj_dropout
        self.activation_dropout = activation_dropout
        self.hidden_dropout = hidden_dropout
        self.max_source_positions = max_source_positions
        self.no_scale_embedding = no_scale_embedding
        self.hidden_act = hidden_act
        self.conformer_conv_dropout = conformer_conv_dropout
        self.position_embeddings_type = position_embeddings_type
        self.attention_dropout = attention_dropout
        self.rotary_embedding_base = rotary_embedding_base
        self.layerdrop = layerdrop
        self.final_dropout = final_dropout
        self.vocab_size = vocab_size
        self.ctc_loss_reduction = ctc_loss_reduction
        self.ctc_zero_infinity = ctc_zero_infinity
        super().__init__(**kwargs)