#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/moss_transcribe_diarize/modular_moss_transcribe_diarize.py.
#               Do NOT edit this file manually as any edits will be overwritten by the generation of
#             the file from the modular. If any change should be done, please apply the change to the
#                          modular_moss_transcribe_diarize.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2026 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.

from huggingface_hub.dataclasses import strict

from ...configuration_utils import PreTrainedConfig, SubConfigSpec
from ...utils import auto_docstring
from ..auto import AutoConfig


@auto_docstring(checkpoint="hf-audio/MOSS-Transcribe-Diarize-HF")
@strict
class MossTranscribeDiarizeAudioConfig(PreTrainedConfig):
    r"""
    max_source_positions (`int`, *optional*, defaults to 1500):
        The maximum sequence length of log-mel filter-bank features that this model might ever be used with.

    Example:

    ```python
    >>> from transformers import MossTranscribeDiarizeAudioConfig, MossTranscribeDiarizeAudioModel

    >>> # Initializing a MossTranscribeDiarizeAudioConfig
    >>> configuration = MossTranscribeDiarizeAudioConfig()

    >>> # Initializing a MossTranscribeDiarizeAudioModel (with random weights)
    >>> model = MossTranscribeDiarizeAudioModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "moss_transcribe_diarize_audio"
    attribute_map = {
        "d_model": "hidden_size",
        "encoder_layers": "num_hidden_layers",
        "encoder_attention_heads": "num_attention_heads",
        "encoder_ffn_dim": "intermediate_size",
    }

    num_mel_bins: int = 80
    num_hidden_layers: int = 24
    num_attention_heads: int = 16
    intermediate_size: int = 4096
    activation_function: str = "gelu"
    hidden_size: int = 1024
    dropout: float | int = 0.0
    attention_dropout: float | int = 0.0
    activation_dropout: float | int = 0.0
    initializer_range: float = 0.02
    max_source_positions: int = 1500


@auto_docstring(checkpoint="hf-audio/MOSS-Transcribe-Diarize-HF")
@strict
class MossTranscribeDiarizeConfig(PreTrainedConfig):
    r"""
    audio_merge_size (`int`, *optional*, defaults to 4):
        Number of consecutive Whisper encoder frames concatenated before the multi-modal projector.
    audio_chunk_size (`int`, *optional*, defaults to 480000):
        Whisper encoder window size in raw audio samples, used with `padding_mask` to recover `audio_chunk_mapping`.

    Example:

    ```python
    >>> from transformers import MossTranscribeDiarizeForConditionalGeneration, MossTranscribeDiarizeConfig

    >>> # Initializing a MossTranscribeDiarize configuration
    >>> configuration = MossTranscribeDiarizeConfig()

    >>> # Initializing a model from the configuration
    >>> model = MossTranscribeDiarizeForConditionalGeneration(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "moss_transcribe_diarize"
    sub_configs_defaults = {
        "audio_config": MossTranscribeDiarizeAudioConfig,
        "text_config": SubConfigSpec(
            config_class=AutoConfig,
            model_type="qwen3",
            init_kwargs={
                "hidden_size": 1024,
                "intermediate_size": 3072,
                "num_hidden_layers": 28,
                "num_attention_heads": 16,
                "num_key_value_heads": 8,
                "max_position_embeddings": 131_072,
                "rope_parameters": {"rope_theta": 1_000_000.0, "rope_type": "default"},
            },
        ),
    }

    audio_config: dict | PreTrainedConfig | None = None
    text_config: dict | PreTrainedConfig | None = None

    audio_token_id: int = 151671
    projector_hidden_act: str = "silu"
    projector_bias: bool = True
    keys_to_ignore_at_inference = ["past_key_values"]
    audio_merge_size: int = 4
    audio_chunk_size: int = 480_000
    tie_word_embeddings: bool = True

    @property
    def adaptor_input_dim(self) -> int:
        return self.audio_config.hidden_size * self.audio_merge_size


__all__ = ["MossTranscribeDiarizeConfig", "MossTranscribeDiarizeAudioConfig"]
