Skip to content

Fix/pe audio video bugs #45886

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
zucchini-nlp merged 6 commits into from
May 12, 2026
+16 −6
Merged

Fix/pe audio video bugs #45886

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
0bc3833
Register correct mapping
massimilianoviola May 10, 2026
65fd8d4
set output_hidden_states in get_text_*_embeds helpers
massimilianoviola May 10, 2026
6cbfa4e
point to get_*_embeds in forward error message
massimilianoviola May 10, 2026
9c81780
Populate PE AV documentation
massimilianoviola May 10, 2026
3f7312c
Revert "Populate PE AV documentation"
massimilianoviola May 11, 2026
f98e891
Merge branch 'main' into fix/pe-audio-video-bugs
massimilianoviola May 11, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion src/transformers/models/pe_audio_video/modeling_pe_audio_video.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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]
Expand Down Expand Up @@ -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]
Expand All @@ -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]
Expand All @@ -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(
Expand Down
8 changes: 7 additions & 1 deletion src/transformers/models/pe_audio_video/modular_pe_audio_video.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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]
Expand Down Expand Up @@ -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]
Expand All @@ -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]
Expand All @@ -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(
Expand Down
6 changes: 2 additions & 4 deletions src/transformers/models/pe_audio_video/processing_pe_audio_video.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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)
Comment on lines +18 to +19

@zucchini-nlp zucchini-nlp May 11, 2026

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

niiice!



__all__ = ["PeAudioVideoProcessor"]
Loading