Change the way tensor is reshaped in BartAttention (from .view to .reshape) (#21860)

* Change the .view call to .reshape

* Change the .view call to .reshape to all the copies from bart attention

* Fix copies and style

* Fix copies and style

* Fix copies and style

* Fix copies and style

* Fix copies and style

* Revert unneccessary changes

* Revert unneccessary changes

* Revert unneccessary changes

* Revert unneccessary changes

src/transformers/models/wav2vec2/modeling_wav2vec2.py

@@ -574,8 +574,8 @@ class Wav2Vec2Attention(nn.Module):
 
         proj_shape = (bsz * self.num_heads, -1, self.head_dim)
         query_states = self._shape(query_states, tgt_len, bsz).view(*proj_shape)
-        key_states = key_states.view(*proj_shape)
-        value_states = value_states.view(*proj_shape)
+        key_states = key_states.reshape(*proj_shape)
+        value_states = value_states.reshape(*proj_shape)
 
         src_len = key_states.size(1)
         attn_weights = torch.bmm(query_states, key_states.transpose(1, 2))

src/transformers/models/whisper/modeling_whisper.py

@@ -319,8 +319,8 @@ class WhisperAttention(nn.Module):
 
         proj_shape = (bsz * self.num_heads, -1, self.head_dim)
         query_states = self._shape(query_states, tgt_len, bsz).view(*proj_shape)
-        key_states = key_states.view(*proj_shape)
-        value_states = value_states.view(*proj_shape)
+        key_states = key_states.reshape(*proj_shape)
+        value_states = value_states.reshape(*proj_shape)
 
         src_len = key_states.size(1)
         attn_weights = torch.bmm(query_states, key_states.transpose(1, 2))