# coding=utf-8
# Copyright 2024 NAVER Cloud Corp. and the HuggingFace Inc. team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""MambaMia video-audio compressor configuration"""

from transformers import AutoConfig
from transformers.configuration_utils import PretrainedConfig


class MambaMiaVideoAudioCompressorConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a MambaMia video-audio compressor.

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PretrainedConfig`] for more information.

    Args:
        input_size (`int`, *optional*, defaults to 1280):
            Input embedding dimension (e.g., 1280 for Whisper encoder output).
        output_size (`int`, *optional*, defaults to 2048):
            Output embedding dimension (e.g., 2048 for LLM hidden size).
        chunk_size (`int`, *optional*, defaults to 25):
            Number of tokens per chunk (i.e., 1 second at 25Hz).
        num_hidden_layers (`int`, *optional*, defaults to 1):
            Number of MambaMia2 layers.
        hidden_size (`int`, *optional*, defaults to 3072):
            Internal hidden size. Must be divisible by 24.
    """

    model_type = "mambamia_videoaudio_compressor"

    def __init__(
        self,
        input_size: int = 1280,
        output_size: int = 2048,
        chunk_size: int = 25,
        num_hidden_layers: int = 1,
        hidden_size: int = 3072,
        **kwargs,
    ):
        super().__init__(**kwargs)
        self.input_size = input_size
        self.output_size = output_size
        self.chunk_size = chunk_size
        self.num_hidden_layers = num_hidden_layers
        self.hidden_size = hidden_size


AutoConfig.register("mambamia_videoaudio_compressor", MambaMiaVideoAudioCompressorConfig)

__all__ = ["MambaMiaVideoAudioCompressorConfig"]