File size: 4,438 Bytes
3113179
 
 
 
c967f9a
3113179
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c967f9a
3113179
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c967f9a
71c53d9
3113179
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
from dataclasses import dataclass
from typing import Optional, Tuple
import torch
from transformers.file_utils import ModelOutput
from .wav2vec2fsr_config import W2V2FSRConfig


@dataclass
class SpeechClassifierOutput(ModelOutput):
    loss: Optional[torch.FloatTensor] = None
    logits: torch.FloatTensor = None
    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
    attentions: Optional[Tuple[torch.FloatTensor]] = None
    
    
import torch
import torch.nn as nn
from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss

from transformers.models.wav2vec2.modeling_wav2vec2 import (
    Wav2Vec2PreTrainedModel,
    Wav2Vec2Model
)


class Wav2Vec2ClassificationHead(nn.Module):
    """Head for wav2vec classification task."""
    config_class = W2V2FSRConfig

    def __init__(self, config):
        super().__init__()
        self.dense = nn.Linear(config.hidden_size, config.hidden_size)
        self.dropout = nn.Dropout(config.final_dropout)
        self.out_proj = nn.Linear(config.hidden_size, config.num_labels)

    def forward(self, features, **kwargs):
        x = features
        x = self.dropout(x)
        x = self.dense(x)
        x = torch.tanh(x)
        x = self.dropout(x)
        x = self.out_proj(x)
        return x


class Wav2Vec2ForSpeechClassification(Wav2Vec2PreTrainedModel):
    config_class = W2V2FSRConfig
    
    def __init__(self, config):
        super().__init__(config)
        self.num_labels = config.num_labels
        self.pooling_mode = config.pooling_mode
        self.config = config

        self.wav2vec2 = Wav2Vec2Model(config)
        self.classifier = Wav2Vec2ClassificationHead(config)

        self.init_weights()

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

    def merged_strategy(
            self,
            hidden_states,
            mode="mean"
    ):
        if mode == "mean":
            outputs = torch.mean(hidden_states, dim=1)
        elif mode == "sum":
            outputs = torch.sum(hidden_states, dim=1)
        elif mode == "max":
            outputs = torch.max(hidden_states, dim=1)[0]
        else:
            raise Exception(
                "The pooling method hasn't been defined! Your pooling mode must be one of these ['mean', 'sum', 'max']")

        return outputs

    def forward(
            self,
            input_values,
            attention_mask=None,
            output_attentions=None,
            output_hidden_states=None,
            return_dict=None,
            labels=None,
    ):
        return_dict = return_dict if return_dict is not None else self.config.use_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]
        hidden_states = self.merged_strategy(hidden_states, mode=self.pooling_mode)
        logits = self.classifier(hidden_states)

        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 = MSELoss()
                loss = loss_fct(logits.view(-1, self.num_labels), labels)
            elif self.config.problem_type == "single_label_classification":
                loss_fct = CrossEntropyLoss()
                loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
            elif self.config.problem_type == "multi_label_classification":
                loss_fct = 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 SpeechClassifierOutput(
            loss=loss,
            logits=logits,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )