Update modeling_bert_vits2.py

modeling_bert_vits2.py

@@ -32,7 +32,7 @@ from transformers.modeling_outputs import (
 )
 from transformers.models.bert.modeling_bert import BertModel
 from transformers.modeling_utils import PreTrainedModel
-from transformers.utils import add_start_docstrings, add_start_docstrings_to_model_forward, logging, replace_return_docstrings
+from transformers.utils import logging
 
 logger = logging.get_logger(__name__)
 
@@ -1404,58 +1404,6 @@ class BertVits2PreTrainedModel(PreTrainedModel):
                 module.weight.data[module.padding_idx].zero_()
 
 
-BERT_VITS2_START_DOCSTRING = r"""
-    This model inherits from [`PreTrainedModel`]. Check the superclass documentation for the generic methods the
-    library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads
-    etc.)
-
-    This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass.
-    Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage
-    and behavior.
-
-    Parameters:
-        config ([`BertVits2Config`]):
-            Model configuration class with all the parameters of the model. Initializing with a config file does not
-            load the weights associated with the model, only the configuration. Check out the
-            [`~PreTrainedModel.from_pretrained`] method to load the model weights.
-"""
-
-
-BERT_VITS2_INPUTS_DOCSTRING = r"""
-    Args:
-        input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`):
-            Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide
-            it.
-
-            Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
-            [`PreTrainedTokenizer.__call__`] for details.
-
-            [What are input IDs?](../glossary#input-ids)
-        attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
-            Mask to avoid performing convolution and attention on padding token indices. Mask values selected in `[0,
-            1]`:
-
-            - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **masked**.
-
-            [What are attention masks?](../glossary#attention-mask)
-        speaker_id (`int`, *optional*):
-            Which speaker embedding to use. Only used for multispeaker models.
-        output_attentions (`bool`, *optional*):
-            Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
-            tensors for more detail.
-        output_hidden_states (`bool`, *optional*):
-            Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
-            more detail.
-        return_dict (`bool`, *optional*):
-            Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
-"""
-
-
-@add_start_docstrings(
-    "The complete VITS model, for text-to-speech synthesis.",
-    BERT_VITS2_START_DOCSTRING,
-)
 class BertVits2Model(BertVits2PreTrainedModel):
     def __init__(self, config):
         super().__init__(config)
@@ -1492,8 +1440,6 @@ class BertVits2Model(BertVits2PreTrainedModel):
     def get_encoder(self):
         return self.text_encoder
 
-    @add_start_docstrings_to_model_forward(BERT_VITS2_INPUTS_DOCSTRING)
-    @replace_return_docstrings(output_type=BertVits2ModelOutput)
     def forward(
         self,
         input_ids: Optional[torch.Tensor] = None,