|
from dataclasses import dataclass |
|
from typing import Optional, Tuple |
|
import torch |
|
import torch.nn as nn |
|
from transformers.models.wav2vec2.modeling_wav2vec2 import ( |
|
Wav2Vec2PreTrainedModel, |
|
Wav2Vec2Model |
|
) |
|
|
|
@dataclass |
|
class AudioClassifierOutput: |
|
loss: Optional[torch.FloatTensor] = None |
|
logits: torch.FloatTensor = None |
|
hidden_states: Optional[Tuple[torch.FloatTensor]] = None |
|
attentions: Optional[Tuple[torch.FloatTensor]] = None |
|
|
|
class Wav2Vec2ForAudioClassification(Wav2Vec2PreTrainedModel): |
|
def __init__(self, config): |
|
super().__init__(config) |
|
self.wav2vec2 = Wav2Vec2Model(config) |
|
self.classifier = nn.Sequential( |
|
nn.Linear(config.hidden_size, config.classifier_proj_size), |
|
nn.GELU(), |
|
nn.Dropout(config.final_dropout), |
|
nn.Linear(config.classifier_proj_size, config.num_labels) |
|
) |
|
self.init_weights() |
|
|
|
def freeze_feature_encoder(self): |
|
self.wav2vec2.feature_extractor._freeze_parameters() |
|
|
|
def forward( |
|
self, |
|
input_values, |
|
attention_mask=None, |
|
labels=None, |
|
output_attentions=None, |
|
output_hidden_states=None, |
|
return_dict=None, |
|
): |
|
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] |
|
pooled_output = torch.mean(hidden_states, dim=1) |
|
logits = self.classifier(pooled_output) |
|
|
|
loss = None |
|
if labels is not None: |
|
loss_fct = nn.CrossEntropyLoss() |
|
loss = loss_fct(logits.view(-1, self.config.num_labels), labels.view(-1)) |
|
|
|
return AudioClassifierOutput( |
|
loss=loss, |
|
logits=logits, |
|
hidden_states=outputs.hidden_states, |
|
attentions=outputs.attentions, |
|
) |
