diff --git a/src/transformers/models/pe_audio_video/modeling_pe_audio_video.py b/src/transformers/models/pe_audio_video/modeling_pe_audio_video.py
index f5eda9be46a7..48634fde149a 100644
--- a/src/transformers/models/pe_audio_video/modeling_pe_audio_video.py
+++ b/src/transformers/models/pe_audio_video/modeling_pe_audio_video.py
@@ -796,6 +796,7 @@ def get_text_audio_video_embeds(self, input_ids, attention_mask=None):
         text_outputs: MaskedLMOutput = self.text_model(
             input_ids=input_ids,
             attention_mask=attention_mask,
+            output_hidden_states=True,
             return_dict=True,
         )
         text_embeds = text_outputs.hidden_states[-1][:, 0]
@@ -851,6 +852,7 @@ def get_audio_plus_text_embeds(
         text_outputs: MaskedLMOutput = self.text_model(
             input_ids=input_ids,
             attention_mask=attention_mask,
+            output_hidden_states=True,
             return_dict=True,
         )
         text_embeds = text_outputs.hidden_states[-1][:, 0]
@@ -873,6 +875,7 @@ def get_video_plus_text_embeds(
         text_outputs: MaskedLMOutput = self.text_model(
             input_ids=input_ids,
             attention_mask=attention_mask,
+            output_hidden_states=True,
             return_dict=True,
         )
         text_embeds = text_outputs.hidden_states[-1][:, 0]
@@ -893,7 +896,10 @@ def forward(
         **kwargs,
     ) -> PeAudioVideoOutput:
         if sum([input_ids is not None, pixel_values_videos is not None, input_values is not None]) < 2:
-            raise ValueError("At least two of input_ids, pixel_values_videos, or input_values must be provided")
+            raise ValueError(
+                "At least two of input_ids, pixel_values_videos, or input_values must be provided. "
+                "For encoding individual modalities, get_*_embeds methods are available."
+            )
 
         if pixel_values_videos is None:
             outputs = self.audio_model(
diff --git a/src/transformers/models/pe_audio_video/modular_pe_audio_video.py b/src/transformers/models/pe_audio_video/modular_pe_audio_video.py
index fc0d353585fb..649a5da8811e 100644
--- a/src/transformers/models/pe_audio_video/modular_pe_audio_video.py
+++ b/src/transformers/models/pe_audio_video/modular_pe_audio_video.py
@@ -588,6 +588,7 @@ def get_text_audio_video_embeds(self, input_ids, attention_mask=None):
         text_outputs: MaskedLMOutput = self.text_model(
             input_ids=input_ids,
             attention_mask=attention_mask,
+            output_hidden_states=True,
             return_dict=True,
         )
         text_embeds = text_outputs.hidden_states[-1][:, 0]
@@ -643,6 +644,7 @@ def get_audio_plus_text_embeds(
         text_outputs: MaskedLMOutput = self.text_model(
             input_ids=input_ids,
             attention_mask=attention_mask,
+            output_hidden_states=True,
             return_dict=True,
         )
         text_embeds = text_outputs.hidden_states[-1][:, 0]
@@ -665,6 +667,7 @@ def get_video_plus_text_embeds(
         text_outputs: MaskedLMOutput = self.text_model(
             input_ids=input_ids,
             attention_mask=attention_mask,
+            output_hidden_states=True,
             return_dict=True,
         )
         text_embeds = text_outputs.hidden_states[-1][:, 0]
@@ -685,7 +688,10 @@ def forward(
         **kwargs,
     ) -> PeAudioVideoOutput:
         if sum([input_ids is not None, pixel_values_videos is not None, input_values is not None]) < 2:
-            raise ValueError("At least two of input_ids, pixel_values_videos, or input_values must be provided")
+            raise ValueError(
+                "At least two of input_ids, pixel_values_videos, or input_values must be provided. "
+                "For encoding individual modalities, get_*_embeds methods are available."
+            )
 
         if pixel_values_videos is None:
             outputs = self.audio_model(
diff --git a/src/transformers/models/pe_audio_video/processing_pe_audio_video.py b/src/transformers/models/pe_audio_video/processing_pe_audio_video.py
index a03b213b10c5..194abec2bf03 100644
--- a/src/transformers/models/pe_audio_video/processing_pe_audio_video.py
+++ b/src/transformers/models/pe_audio_video/processing_pe_audio_video.py
@@ -15,10 +15,8 @@
 
 
 class PeAudioVideoProcessor(ProcessorMixin):
-    attributes = ["feature_extractor", "video_processor", "tokenizer"]
-    feature_extractor_class = "PeAudioFeatureExtractor"
-    tokenizer_class = "AutoTokenizer"
-    video_processor_class = "PeVideoVideoProcessor"
+    def __init__(self, feature_extractor=None, video_processor=None, tokenizer=None, **kwargs):
+        super().__init__(feature_extractor, video_processor, tokenizer, **kwargs)
 
 
 __all__ = ["PeAudioVideoProcessor"]