modeling.py

from typing import Optional, Tuple, Union
import torch
import torch.nn as nn
import torch.nn.functional as F
from transformers import Wav2Vec2Model, Wav2Vec2PreTrainedModel
from transformers.modeling_outputs import SequenceClassifierOutput
from transformers.models.auto import AutoConfig, AutoModelForAudioClassification

from .configuration import Wav2Vec2DualHypersphereConfig


class Wav2Vec2DualHypersphereForAudioClassification(Wav2Vec2PreTrainedModel):
    config_class = Wav2Vec2DualHypersphereConfig

    def __init__(self, config: Wav2Vec2DualHypersphereConfig):
        super().__init__(config)
        self.num_labels = config.num_labels

        self.wav2vec2 = Wav2Vec2Model(config)
        proj_dim = getattr(config, "classifier_proj_size", 256)
        self.projector = nn.Linear(config.hidden_size, proj_dim)
        self.dropout = nn.Dropout(getattr(config, "final_dropout", 0.1))
        self.classifier = nn.Linear(proj_dim, self.num_labels)

        # Initialize weights and apply final processing
        self.post_init()

    def freeze_feature_extractor(self):
        self.wav2vec2.feature_extractor._freeze_parameters()

    def forward(
        self,
        input_values: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        labels: Optional[torch.Tensor] = None,
    ) -> Union[Tuple, SequenceClassifierOutput]:
        r"""
        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the sequence classification/regression loss.
        """
        return_dict = return_dict if return_dict is not None else self.config.return_dict

        outputs = self.wav2vec2(
            input_values,
            attention_mask=attention_mask,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )
        hidden_states = outputs[0]

        # 1. Temporal Pooling with Attention Mask support
        if attention_mask is not None:
            mask = self.wav2vec2._get_feature_vector_attention_mask(
                hidden_states.shape[1], attention_mask
            )
            mask = mask.unsqueeze(-1).expand_as(hidden_states)
            pooled_768 = (hidden_states * mask).sum(dim=1) / mask.sum(dim=1).clamp(min=1e-9)
        else:
            pooled_768 = hidden_states.mean(dim=1)

        # 2. First Hypersphere Projection (L2 Normalize 768-D)
        norm_pooled_768 = F.normalize(pooled_768, p=2, dim=-1)

        # 3. Intermediate Projection & Dropout
        projected_256 = self.dropout(self.projector(norm_pooled_768))

        # 4. Second Hypersphere Projection (L2 Normalize 256-D)
        norm_projected_256 = F.normalize(projected_256, p=2, dim=-1)

        # 5. Final Classification Logits
        logits = self.classifier(norm_projected_256)

        loss = None
        if labels is not None:
            if self.config.problem_type is None:
                if self.num_labels == 1:
                    self.config.problem_type = "regression"
                elif self.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int):
                    self.config.problem_type = "single_label_classification"
                else:
                    self.config.problem_type = "multi_label_classification"

            if self.config.problem_type == "regression":
                loss_fct = nn.MSELoss()
                if self.num_labels == 1:
                    loss = loss_fct(logits.squeeze(), labels.squeeze())
                else:
                    loss = loss_fct(logits, labels)
            elif self.config.problem_type == "single_label_classification":
                loss_fct = nn.CrossEntropyLoss()
                loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
            elif self.config.problem_type == "multi_label_classification":
                loss_fct = nn.BCEWithLogitsLoss()
                loss = loss_fct(logits, labels)

        if not return_dict:
            output = (logits,) + outputs[2:]
            return ((loss,) + output) if loss is not None else output

        return SequenceClassifierOutput(
            loss=loss,
            logits=logits,
            hidden_states=outputs.hidden_states if hasattr(outputs, "hidden_states") else None,
            attentions=outputs.attentions if hasattr(outputs, "attentions") else None,
        )


# Register model & config with Auto classes
AutoConfig.register("wav2vec2-dual-hypersphere", Wav2Vec2DualHypersphereConfig)
AutoModelForAudioClassification.register(
    Wav2Vec2DualHypersphereConfig, Wav2Vec2DualHypersphereForAudioClassification
)

Wav2Vec2DualHypersphereClassifier = Wav2Vec2DualHypersphereForAudioClassification

__all__ = [
    "Wav2Vec2DualHypersphereConfig",
    "Wav2Vec2DualHypersphereForAudioClassification",
    "Wav2Vec2DualHypersphereClassifier",
]