`bridge.models.qwen3_asr.hf_qwen3_asr.configuration_qwen3_asr`#

Module Contents#

Classes#

`Qwen3ASRAudioEncoderConfig`	This is the configuration class to store the configuration of a [`Qwen3ASRAudioEncoder`]. It is used to instantiate a Qwen3-ASR audio encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the audio encoder of the Qwen2-Audio architecture.
`Qwen3ASRTextConfig`	This is the configuration class to store the configuration of a [`Qwen3ASRTextModel`]. It is used to instantiate a Qwen3-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 Qwen3-ASR-1.7B Qwen/Qwen3-ASR-1.7B
`Qwen3ASRThinkerConfig`	This is the configuration class to store the configuration of a [`Qwen3ASRThinker`]. It is used to instantiate a Qwen3-ASR-Thinker model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the thinker component of the Qwen3-Omni architecture.
`Qwen3ASRConfig`	This is the configuration class to store the configuration of a [`Qwen3ASRForConditionalGeneration`]. It is used to instantiate a Qwen3ASR model according to the specified sub-models configurations, defining the model architecture.

Data#

`logger`
`__all__`

API#

bridge.models.qwen3_asr.hf_qwen3_asr.configuration_qwen3_asr.logger#: ‘get_logger(…)’

class bridge.models.qwen3_asr.hf_qwen3_asr.configuration_qwen3_asr.Qwen3ASRAudioEncoderConfig(

num_mel_bins=128,

encoder_layers=32,

encoder_attention_heads=20,

encoder_ffn_dim=5120,

d_model=1280,

dropout=0,

attention_dropout=0,

activation_function='gelu',

activation_dropout=0,

scale_embedding=False,

initializer_range=0.02,

max_source_positions=1500,

n_window=100,

output_dim=3584,

n_window_infer=400,

conv_chunksize=500,

downsample_hidden_size=480,

**kwargs,

)#

Bases: transformers.configuration_utils.PretrainedConfig

This is the configuration class to store the configuration of a [Qwen3ASRAudioEncoder]. It is used to instantiate a Qwen3-ASR audio encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the audio encoder of the Qwen2-Audio architecture.

e.g. Qwen/Qwen3-ASR-1.7B

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

Parameters:

num_mel_bins (int, optional, defaults to 128) – Number of mel features used per input features. Should correspond to the value used in the Qwen3ASRProcessor class.
encoder_layers (int, optional, defaults to 32) – Number of encoder layers.
encoder_attention_heads (int, optional, defaults to 20) – Number of attention heads for each attention layer in the Transformer encoder.
encoder_ffn_dim (int, optional, defaults to 5120) – Dimensionality of the “intermediate” (often named feed-forward) layer in encoder.
d_model (int, optional, defaults to 1280) – Dimensionality of the layers.
dropout (float, optional, defaults to 0.0) – The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
attention_dropout (float, optional, defaults to 0.0) – The dropout ratio for the attention probabilities.
activation_function (str, optional, defaults to "gelu") – The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "silu" and "gelu_new" are supported.
activation_dropout (float, optional, defaults to 0.0) – The dropout ratio for activations inside the fully connected layer.
scale_embedding (bool, optional, defaults to False) – Scale embeddings by diving by sqrt(d_model).
initializer_range (float, optional, defaults to 0.02) – The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
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.
n_window (int, optional, defaults to 100) – The chunk for conv and flash attn in AudioEncoder.
output_dim (int, optional, defaults to 3584) – The output dimension of AudioEncoder.

Example:

>>> from transformers import Qwen3ASRAudioEncoderConfig, Qwen3ASRAudioEncoder

>>> # Initializing a Qwen3ASRAudioEncoderConfig
>>> configuration = Qwen3ASRAudioEncoderConfig()

>>> # Initializing a Qwen3ASRAudioEncoder (with random weights)
>>> model = Qwen3ASRAudioEncoder(configuration)

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

Initialization

model_type#: ‘qwen3_asr_audio_encoder’

class bridge.models.qwen3_asr.hf_qwen3_asr.configuration_qwen3_asr.Qwen3ASRTextConfig(

vocab_size=151936,

hidden_size=4096,

intermediate_size=22016,

num_hidden_layers=32,

num_attention_heads=32,

num_key_value_heads=32,

head_dim=128,

hidden_act='silu',

max_position_embeddings=128000,

initializer_range=0.02,

rms_norm_eps=1e-06,

use_cache=True,

tie_word_embeddings=False,

rope_theta=5000000.0,

rope_scaling=None,

attention_bias=False,

attention_dropout=0.0,

**kwargs,

)#

Bases: transformers.configuration_utils.PretrainedConfig

This is the configuration class to store the configuration of a [Qwen3ASRTextModel]. It is used to instantiate a Qwen3-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 Qwen3-ASR-1.7B Qwen/Qwen3-ASR-1.7B

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

Parameters:

vocab_size (int, optional, defaults to 151936) – Vocabulary size of the Qwen3ASR model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling [Qwen3ASRModel]
hidden_size (int, optional, defaults to 4096) – Dimension of the hidden representations.
intermediate_size (int, optional, defaults to 22016) – Dimension of the MLP representations.
num_hidden_layers (int, optional, defaults to 32) – Number of hidden layers in the Transformer encoder.
num_attention_heads (int, optional, defaults to 32) – Number of attention heads for each attention layer in the Transformer encoder.
num_key_value_heads (int, optional, defaults to 32) – This is the number of key_value heads that should be used to implement Grouped Query Attention. If num_key_value_heads=num_attention_heads, the model will use Multi Head Attention (MHA), if num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details, check out this paper. If it is not specified, will default to 32.
head_dim (int, optional, defaults to 128) – The dimension of the head. If not specified, will default to hidden_size // num_attention_heads.
hidden_act (str or function, optional, defaults to "silu") – The non-linear activation function (function or string) in the decoder.
max_position_embeddings (int, optional, defaults to 128000) – The maximum sequence length that this model might ever be used with.
initializer_range (float, optional, defaults to 0.02) – The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
rms_norm_eps (float, optional, defaults to 1e-06) – The epsilon used by the rms normalization layers.
use_cache (bool, optional, defaults to True) – Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if config.is_decoder=True.
tie_word_embeddings (bool, optional, defaults to False) – Whether the model’s input and output word embeddings should be tied.
rope_theta (float, optional, defaults to 5000000.0) – The base period of the RoPE embeddings.
rope_scaling (Dict, optional) – Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type and you expect the model to work on longer max_position_embeddings, we recommend you to update this value accordingly. Expected contents: rope_type (str): The sub-variant of RoPE to use. Can be one of [‘default’, ‘linear’, ‘dynamic’, ‘yarn’, ‘longrope’, ‘llama3’], with ‘default’ being the original RoPE implementation. factor (float, optional): Used with all rope types except ‘default’. The scaling factor to apply to the RoPE embeddings. In most scaling types, a factor of x will enable the model to handle sequences of length x * original maximum pre-trained length. original_max_position_embeddings (int, optional): Used with ‘dynamic’, ‘longrope’ and ‘llama3’. The original max position embeddings used during pretraining. attention_factor (float, optional): Used with ‘yarn’ and ‘longrope’. The scaling factor to be applied on the attention computation. If unspecified, it defaults to value recommended by the implementation, using the factor field to infer the suggested value. beta_fast (float, optional): Only used with ‘yarn’. Parameter to set the boundary for extrapolation (only) in the linear ramp function. If unspecified, it defaults to 32. beta_slow (float, optional): Only used with ‘yarn’. Parameter to set the boundary for interpolation (only) in the linear ramp function. If unspecified, it defaults to 1. short_factor (list[float], optional): Only used with ‘longrope’. The scaling factor to be applied to short contexts (< original_max_position_embeddings). Must be a list of numbers with the same length as the hidden size divided by the number of attention heads divided by 2 long_factor (list[float], optional): Only used with ‘longrope’. The scaling factor to be applied to long contexts (< original_max_position_embeddings). Must be a list of numbers with the same length as the hidden size divided by the number of attention heads divided by 2 low_freq_factor (float, optional): Only used with ‘llama3’. Scaling factor applied to low frequency components of the RoPE high_freq_factor (float, optional): Only used with ‘llama3’. Scaling factor applied to high frequency components of the RoPE
attention_bias (bool, defaults to False, optional, defaults to False) – Whether to use a bias in the query, key, value and output projection layers during self-attention.
attention_dropout (float, optional, defaults to 0.0) – The dropout ratio for the attention probabilities.

>>> from transformers import Qwen3ASRTextModel, Qwen3ASRTextConfig

>>> # Initializing a Qwen3ASR style configuration
>>> configuration = Qwen3ASRTextConfig()

>>> # Initializing a model from the Qwen3-VL-7B style configuration
>>> model = Qwen3ASRTextModel(configuration)

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

Initialization

model_type#: ‘qwen3_asr_text’

base_config_key#: ‘text_config’

class bridge.models.qwen3_asr.hf_qwen3_asr.configuration_qwen3_asr.Qwen3ASRThinkerConfig(

audio_config=None,

text_config=None,

audio_token_id=151646,

audio_start_token_id=151647,

user_token_id=872,

initializer_range=0.02,

**kwargs,

)#

Bases: transformers.configuration_utils.PretrainedConfig

This is the configuration class to store the configuration of a [Qwen3ASRThinker]. It is used to instantiate a Qwen3-ASR-Thinker model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the thinker component of the Qwen3-Omni architecture.

e.g. Qwen/Qwen3-ASR-1.7B

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

Parameters:

audio_config (dict, optional) – The config dictionary of the audio backbone.
text_config (dict, optional) – The config dictionary of the text backbone.
audio_token_id (int, optional, defaults to 151646) – The audio token id to encode the audio prompt.
audio_start_token_id (int, optional, defaults to 151647) – The audio start token id to encode the audio prompt.
user_token_id (int, optional, defaults to 872) – The user token id to encode the user token.
initializer_range (float, optional, defaults to 0.02) – The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

Example:

>>> from transformers import Qwen3ASRThinkerModel, Qwen3ASRThinkerConfig

>>> # Initializing a default Qwen3ASRThinkerConfig
>>> configuration = Qwen3ASRThinkerConfig()

>>> # Initializing a model (with random weights) from the default configuration
>>> model = Qwen3ASRThinkerModel(configuration)

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

Initialization

model_type#: ‘qwen3_asr_thinker’

attribute_map#: None

sub_configs#: None

class bridge.models.qwen3_asr.hf_qwen3_asr.configuration_qwen3_asr.Qwen3ASRConfig(thinker_config=None, support_languages=None, **kwargs)#

Bases: transformers.configuration_utils.PretrainedConfig

This is the configuration class to store the configuration of a [Qwen3ASRForConditionalGeneration]. It is used to instantiate a Qwen3ASR model according to the specified sub-models configurations, defining the model architecture.

Instantiating a configuration with the defaults will yield a similar configuration to that of the Qwen/Qwen3-ASR-1.7B architecture.

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

Parameters:

thinker_config (dict, optional) – Configuration of the underlying thinker sub-model.
support_languages (List[str], optional) – The languages supported by the model.

Example:

>>> from transformers import (
...     Qwen3ASRThinkerConfig,
...     Qwen3ASRForConditionalGeneration,
...     Qwen3ASRConfig,
... )

>>> # Initializing a Qwen3ASR style configuration
>>> configuration = Qwen3ASRConfig()

>>> # Initializing a model from the configuration
>>> model = Qwen3ASRForConditionalGeneration(configuration)

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

Initialization

model_type#: ‘qwen3_asr’

sub_configs#: None

get_text_config( decoder=False, ) → transformers.configuration_utils.PretrainedConfig#

Returns the config that is meant to be used with text IO. On most models, it is the original config instance itself. On specific composite models, it is under a set of valid names.

Parameters:: decoder (Optional[bool], optional, defaults to False) – If set to True, then only search for decoder config names.

bridge.models.qwen3_asr.hf_qwen3_asr.configuration_qwen3_asr.__all__#: [‘Qwen3ASRConfig’, ‘Qwen3ASRThinkerConfig’, ‘Qwen3ASRAudioEncoderConfig’]

bridge.models.qwen3_asr.hf_qwen3_asr.configuration_qwen3_asr#

Module Contents#

Classes#

Data#

API#

`bridge.models.qwen3_asr.hf_qwen3_asr.configuration_qwen3_asr`#