#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/vibevoice_asr/modular_vibevoice_asr.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_vibevoice_asr.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2026 Microsoft 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.


from ...configuration_utils import PretrainedConfig
from ..auto import CONFIG_MAPPING, AutoConfig


class VibeVoiceAsrConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`VibeVoiceAsrForConditionalGeneration`]. It is used
    to instantiate a VibeVoice ASR model according to the specified arguments, defining the model architecture.
    Instantiating a configuration with the defaults will yield a similar configuration to that of Microsoft's VibeVoice
    ASR architecture.

    e.g. [microsoft/VibeVoice-ASR](https://huggingface.co/microsoft/VibeVoice-ASR)

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

    Args:
        acoustic_tokenizer_encoder_config (`Union[VibeVoiceAcousticTokenizerConfig, dict]`, *optional*):
            The config object or dictionary of the acoustic tokenizer. This tokenizer extracts acoustic features from audio.
        semantic_tokenizer_encoder_config (`Union[VibeVoiceAcousticTokenizerConfig, dict]`, *optional*):
            The config object or dictionary of the semantic tokenizer. This tokenizer extracts semantic features from audio.
        text_config (`Union[AutoConfig, dict]`, *optional*, defaults to `Qwen2Config`):
            The config object or dictionary of the text backbone (language model).
        audio_token_id (`int`, *optional*, defaults to 151648):
            The audio token index to encode the audio prompt.
        audio_bos_token_id (`int`, *optional*, defaults to 151646):
            The audio begin-of-sequence token index.
        audio_eos_token_id (`int`, *optional*, defaults to 151647):
            The audio end-of-sequence token index.
        acoustic_tokenizer_chunk_size (`int`, *optional*, defaults to 1440000):
            The chunk size (in number of samples) to use when tokenizer audio inputs. Default corresponds to 60 seconds at 24kHz.

    Example:

    ```python
    >>> from transformers import VibeVoiceAsrForConditionalGeneration, VibeVoiceAsrConfig, VibeVoiceAcousticTokenizerEncoderConfig, Qwen2Config

    >>> # Initializing VibeVoice acoustic and semantic encoder configs
    >>> acoustic_config = VibeVoiceAcousticTokenizerEncoderConfig()
    >>> semantic_config = VibeVoiceAcousticTokenizerEncoderConfig(hidden_size=128)

    >>> # Initializing a Qwen2 config
    >>> text_config = Qwen2Config()

    >>> # Initializing a VibeVoice ASR configuration
    >>> configuration = VibeVoiceAsrConfig(acoustic_config, semantic_config, text_config)

    >>> # Initializing a model from the vibevoice_asr style configuration
    >>> model = VibeVoiceAsrForConditionalGeneration(configuration)

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

    model_type = "vibevoice_asr"
    sub_configs = {
        "acoustic_tokenizer_encoder_config": AutoConfig,
        "semantic_tokenizer_encoder_config": AutoConfig,
        "text_config": AutoConfig,
    }

    def __init__(
        self,
        acoustic_tokenizer_encoder_config=None,
        semantic_tokenizer_encoder_config=None,
        text_config=None,
        audio_token_id=151648,
        audio_bos_token_id=151646,
        audio_eos_token_id=151647,
        acoustic_tokenizer_chunk_size=1440000,
        **kwargs,
    ):
        if isinstance(acoustic_tokenizer_encoder_config, dict):
            acoustic_tokenizer_encoder_config["model_type"] = acoustic_tokenizer_encoder_config.get(
                "model_type", "vibevoice_acoustic_tokenizer_encoder"
            )
            acoustic_tokenizer_encoder_config = CONFIG_MAPPING[acoustic_tokenizer_encoder_config["model_type"]](
                **acoustic_tokenizer_encoder_config
            )
        elif acoustic_tokenizer_encoder_config is None:
            acoustic_tokenizer_encoder_config = CONFIG_MAPPING["vibevoice_acoustic_tokenizer_encoder"]()
        self.acoustic_tokenizer_encoder_config = acoustic_tokenizer_encoder_config

        if isinstance(semantic_tokenizer_encoder_config, dict):
            semantic_tokenizer_encoder_config["model_type"] = semantic_tokenizer_encoder_config.get(
                "model_type", "vibevoice_acoustic_tokenizer_encoder"
            )
            semantic_tokenizer_encoder_config = CONFIG_MAPPING[semantic_tokenizer_encoder_config["model_type"]](
                **semantic_tokenizer_encoder_config
            )
        elif semantic_tokenizer_encoder_config is None:
            semantic_tokenizer_encoder_config = CONFIG_MAPPING["vibevoice_acoustic_tokenizer_encoder"](hidden_size=128)
        self.semantic_tokenizer_encoder_config = semantic_tokenizer_encoder_config

        if isinstance(text_config, dict):
            text_config["model_type"] = text_config.get("model_type", "qwen2")
            text_config = CONFIG_MAPPING[text_config["model_type"]](**text_config)
        elif text_config is None:
            text_config = CONFIG_MAPPING["qwen2"]()
        self.text_config = text_config

        self.audio_token_id = audio_token_id
        self.audio_bos_token_id = audio_bos_token_id
        self.audio_eos_token_id = audio_eos_token_id
        self.acoustic_tokenizer_chunk_size = acoustic_tokenizer_chunk_size

        super().__init__(**kwargs)


__all__ = ["VibeVoiceAsrConfig"]