huggingface · yonigozlan · Jan 8, 2026 · Oct 15, 2025 · Oct 15, 2025 · Oct 15, 2025
diff --git a/docs/source/en/model_doc/align.md b/docs/source/en/model_doc/align.md
@@ -166,6 +166,7 @@ for label, score in zip(candidate_labels, probs):
 ## AlignProcessor
 
 [[autodoc]] AlignProcessor
+    - __call__
 
 ## AlignModel
 

diff --git a/docs/source/en/model_doc/altclip.md b/docs/source/en/model_doc/altclip.md
@@ -126,3 +126,4 @@ for label, prob in zip(labels, probs[0]):
 ## AltCLIPProcessor
 
 [[autodoc]] AltCLIPProcessor
+    - __call__
diff --git a/docs/source/en/model_doc/aria.md b/docs/source/en/model_doc/aria.md
@@ -149,6 +149,7 @@ print(response)
 ## AriaProcessor
 
 [[autodoc]] AriaProcessor
+    - __call__
 
 ## AriaTextConfig
 

diff --git a/docs/source/en/model_doc/audioflamingo3.md b/docs/source/en/model_doc/audioflamingo3.md
@@ -390,6 +390,7 @@ are forwarded, so you can tweak padding or tensor formats just like when calling
 ## AudioFlamingo3Processor
 
 [[autodoc]] AudioFlamingo3Processor
+    - __call__
 
 ## AudioFlamingo3Encoder
 

diff --git a/docs/source/en/model_doc/aya_vision.md b/docs/source/en/model_doc/aya_vision.md
@@ -260,6 +260,7 @@ print(processor.tokenizer.decode(generated[0], skip_special_tokens=True))
 ## AyaVisionProcessor
 
 [[autodoc]] AyaVisionProcessor
+    - __call__
 
 ## AyaVisionConfig
 

diff --git a/docs/source/en/model_doc/blip-2.md b/docs/source/en/model_doc/blip-2.md
@@ -72,6 +72,7 @@ If you're interested in submitting a resource to be included here, please feel f
 ## Blip2Processor
 
 [[autodoc]] Blip2Processor
+    - __call__
 
 ## Blip2VisionModel
 

diff --git a/docs/source/en/model_doc/blip.md b/docs/source/en/model_doc/blip.md
@@ -99,6 +99,7 @@ Refer to this [notebook](https://github.com/huggingface/notebooks/blob/main/exam
 ## BlipProcessor
 
 [[autodoc]] BlipProcessor
+    - __call__
 
 ## BlipImageProcessor
 

diff --git a/docs/source/en/model_doc/chameleon.md b/docs/source/en/model_doc/chameleon.md
@@ -182,6 +182,7 @@ model = ChameleonForConditionalGeneration.from_pretrained(
 ## ChameleonProcessor
 
 [[autodoc]] ChameleonProcessor
+    - __call__
 
 ## ChameleonImageProcessor
 

diff --git a/docs/source/en/model_doc/chinese_clip.md b/docs/source/en/model_doc/chinese_clip.md
@@ -98,6 +98,7 @@ Currently, following scales of pretrained Chinese-CLIP models are available on
 ## ChineseCLIPProcessor
 
 [[autodoc]] ChineseCLIPProcessor
+    - __call__
 
 ## ChineseCLIPModel
 

diff --git a/docs/source/en/model_doc/clap.md b/docs/source/en/model_doc/clap.md
@@ -79,6 +79,7 @@ print(f"Text embeddings: {text_features}")
 ## ClapProcessor
 
 [[autodoc]] ClapProcessor
+    - __call__
 
 ## ClapModel
 

diff --git a/docs/source/en/model_doc/clip.md b/docs/source/en/model_doc/clip.md
@@ -119,6 +119,7 @@ print(f"Most likely label: {most_likely_label} with probability: {probs[0][most_
 ## CLIPProcessor
 
 [[autodoc]] CLIPProcessor
+    - __call__
 
 ## CLIPModel
 

diff --git a/docs/source/en/model_doc/clipseg.md b/docs/source/en/model_doc/clipseg.md
@@ -84,6 +84,7 @@ A list of official Hugging Face and community (indicated by 🌎) resources to h
 ## CLIPSegProcessor
 
 [[autodoc]] CLIPSegProcessor
+    - __call__
 
 ## CLIPSegModel
 

diff --git a/docs/source/en/model_doc/cohere2_vision.md b/docs/source/en/model_doc/cohere2_vision.md
@@ -139,3 +139,4 @@ print(outputs)
 ## Cohere2VisionProcessor
 
 [[autodoc]] Cohere2VisionProcessor
+    - __call__
diff --git a/docs/source/en/model_doc/colpali.md b/docs/source/en/model_doc/colpali.md
@@ -164,6 +164,7 @@ print(scores)
 ## ColPaliProcessor
 
 [[autodoc]] ColPaliProcessor
+    - __call__
 
 ## ColPaliForRetrieval
 

diff --git a/docs/source/en/model_doc/colqwen2.md b/docs/source/en/model_doc/colqwen2.md
@@ -189,6 +189,7 @@ processor = ColQwen2Processor.from_pretrained(model_name)
 ## ColQwen2Processor
 
 [[autodoc]] ColQwen2Processor
+    - __call__
 
 ## ColQwen2ForRetrieval
 

diff --git a/docs/source/en/model_doc/deepseek_vl.md b/docs/source/en/model_doc/deepseek_vl.md
@@ -209,6 +209,7 @@ model = DeepseekVLForConditionalGeneration.from_pretrained(
 ## DeepseekVLProcessor
 
 [[autodoc]] DeepseekVLProcessor
+    - __call__
 
 ## DeepseekVLImageProcessor
 

diff --git a/docs/source/en/model_doc/deepseek_vl_hybrid.md b/docs/source/en/model_doc/deepseek_vl_hybrid.md
@@ -208,6 +208,7 @@ model = DeepseekVLHybridForConditionalGeneration.from_pretrained(
 ## DeepseekVLHybridProcessor
 
 [[autodoc]] DeepseekVLHybridProcessor
+    - __call__
 
 ## DeepseekVLHybridImageProcessor
 

diff --git a/docs/source/en/model_doc/emu3.md b/docs/source/en/model_doc/emu3.md
@@ -155,6 +155,7 @@ for i, image in enumerate(images['pixel_values']):
 ## Emu3Processor
 
 [[autodoc]] Emu3Processor
+    - __call__
 
 ## Emu3ImageProcessor
 

diff --git a/docs/source/en/model_doc/ernie4_5_vl_moe.md b/docs/source/en/model_doc/ernie4_5_vl_moe.md
@@ -201,6 +201,7 @@ print(output_text)
 ## Ernie4_5_VL_MoeProcessor
 
 [[autodoc]] Ernie4_5_VL_MoeProcessor
+    - __call__
 
 ## Ernie4_5_VL_MoeTextModel
 

diff --git a/docs/source/en/model_doc/flava.md b/docs/source/en/model_doc/flava.md
@@ -63,6 +63,7 @@ This model was contributed by [aps](https://huggingface.co/aps). The original co
 ## FlavaProcessor
 
 [[autodoc]] FlavaProcessor
+    - __call__
 
 ## FlavaImageProcessor
 

diff --git a/docs/source/en/model_doc/florence2.md b/docs/source/en/model_doc/florence2.md
@@ -171,6 +171,7 @@ print(parsed_answer)
 ## Florence2Processor
 
 [[autodoc]] Florence2Processor
+    - __call__
 
 ## Florence2Model
 

diff --git a/docs/source/en/model_doc/gemma3.md b/docs/source/en/model_doc/gemma3.md
@@ -243,6 +243,7 @@ visualizer("<img>What is shown in this image?")
 ## Gemma3Processor
 
 [[autodoc]] Gemma3Processor
+    - __call__
 
 ## Gemma3TextConfig
 

diff --git a/docs/source/en/model_doc/gemma3n.md b/docs/source/en/model_doc/gemma3n.md
@@ -161,6 +161,7 @@ echo -e "Plants create energy through a process known as" | transformers run --t
 ## Gemma3nProcessor
 
 [[autodoc]] Gemma3nProcessor
+    - __call__
 
 ## Gemma3nTextConfig
 

diff --git a/docs/source/en/model_doc/glm46v.md b/docs/source/en/model_doc/glm46v.md
@@ -39,6 +39,7 @@ rendered properly in your Markdown viewer.
 ## Glm46VProcessor
 
 [[autodoc]] Glm46VProcessor
+    - __call__
 
 ## Glm46VModel
 

diff --git a/docs/source/en/model_doc/glm4v.md b/docs/source/en/model_doc/glm4v.md
@@ -196,6 +196,7 @@ print(output_text)
 ## Glm4vProcessor
 
 [[autodoc]] Glm4vProcessor
+    - __call__
 
 ## Glm4vVisionModel
 

diff --git a/docs/source/en/model_doc/glmasr.md b/docs/source/en/model_doc/glmasr.md
@@ -16,7 +16,7 @@ limitations under the License.
 ⚠️ Note that this file is in Markdown but contain specific syntax for our doc-builder (similar to MDX) that may not be rendered properly in your Markdown viewer.
 
 -->
-*This model was released on {release_date} and added to Hugging Face Transformers on 2025-12-15.*
+*This model was released on {release_date} and added to Hugging Face Transformers on 2025-12-24.*
 
 
 # GlmAsr
@@ -162,6 +162,7 @@ print(decoded_outputs)
 ## GlmAsrProcessor
 
 [[autodoc]] GlmAsrProcessor
+    - __call__
 
 ## GlmAsrEncoder
 

diff --git a/docs/source/en/model_doc/got_ocr2.md b/docs/source/en/model_doc/got_ocr2.md
@@ -281,6 +281,7 @@ alt="drawing" width="600"/>
 ## GotOcr2Processor
 
 [[autodoc]] GotOcr2Processor
+    - __call__
 
 ## GotOcr2Model
 

diff --git a/docs/source/en/model_doc/granite_speech.md b/docs/source/en/model_doc/granite_speech.md
@@ -160,6 +160,7 @@ for i, transcription in enumerate(transcriptions):
 ## GraniteSpeechProcessor
 
 [[autodoc]] GraniteSpeechProcessor
+    - __call__
 
 ## GraniteSpeechFeatureExtractor
 

diff --git a/docs/source/en/model_doc/granitevision.md b/docs/source/en/model_doc/granitevision.md
@@ -85,6 +85,7 @@ This model was contributed by [Alexander Brooks](https://huggingface.co/abrooks9
 ## LlavaNextProcessor
 
 [[autodoc]] LlavaNextProcessor
+    - __call__
 
 ## LlavaNextForConditionalGeneration
 

diff --git a/docs/source/en/model_doc/grounding-dino.md b/docs/source/en/model_doc/grounding-dino.md
@@ -114,6 +114,7 @@ A list of official Hugging Face and community (indicated by 🌎) resources to h
 ## GroundingDinoProcessor
 
 [[autodoc]] GroundingDinoProcessor
+    - __call__
     - post_process_grounded_object_detection
 
 ## GroundingDinoConfig

diff --git a/docs/source/en/model_doc/instructblip.md b/docs/source/en/model_doc/instructblip.md
@@ -57,6 +57,7 @@ The attributes can be obtained from model config, as `model.config.num_query_tok
 ## InstructBlipProcessor
 
 [[autodoc]] InstructBlipProcessor
+    - __call__
 
 ## InstructBlipVisionModel
 

diff --git a/docs/source/en/model_doc/internvl.md b/docs/source/en/model_doc/internvl.md
@@ -348,6 +348,7 @@ This example showcases how to handle a batch of chat conversations with interlea
 ## InternVLProcessor
 
 [[autodoc]] InternVLProcessor
+    - __call__
 
 ## InternVLVideoProcessor
 

diff --git a/docs/source/en/model_doc/janus.md b/docs/source/en/model_doc/janus.md
@@ -205,6 +205,7 @@ for i, image in enumerate(images['pixel_values']):
 ## JanusProcessor
 
 [[autodoc]] JanusProcessor
+    - __call__
 
 ## JanusImageProcessor
 

diff --git a/docs/source/en/model_doc/kosmos2_5.md b/docs/source/en/model_doc/kosmos2_5.md
@@ -224,6 +224,7 @@ print(generated_text[0])
 ## Kosmos2_5Processor
 
 [[autodoc]] Kosmos2_5Processor
+    - __call__
 
 ## Kosmos2_5Model
 

diff --git a/docs/source/en/model_doc/lfm2_vl.md b/docs/source/en/model_doc/lfm2_vl.md
@@ -82,6 +82,7 @@ processor.batch_decode(outputs, skip_special_tokens=True)[0]
 ## Lfm2VlProcessor
 
 [[autodoc]] Lfm2VlProcessor
+    - __call__
 
 ## Lfm2VlConfig
 

diff --git a/docs/source/en/model_doc/llama4.md b/docs/source/en/model_doc/llama4.md
@@ -416,6 +416,7 @@ model = Llama4ForConditionalGeneration.from_pretrained(
 ## Llama4Processor
 
 [[autodoc]] Llama4Processor
+    - __call__
 
 ## Llama4ImageProcessorFast
 

diff --git a/docs/source/en/model_doc/llava.md b/docs/source/en/model_doc/llava.md
@@ -250,6 +250,7 @@ A list of official Hugging Face and community (indicated by 🌎) resources to h
 ## LlavaProcessor
 
 [[autodoc]] LlavaProcessor
+    - __call__
 
 ## LlavaModel
 

diff --git a/docs/source/en/model_doc/llava_next.md b/docs/source/en/model_doc/llava_next.md
@@ -206,6 +206,7 @@ print(processor.decode(output[0], skip_special_tokens=True))
 ## LlavaNextProcessor
 
 [[autodoc]] LlavaNextProcessor
+    - __call__
 
 ## LlavaNextModel
 

diff --git a/docs/source/en/model_doc/llava_onevision.md b/docs/source/en/model_doc/llava_onevision.md
@@ -298,6 +298,7 @@ model = LlavaOnevisionForConditionalGeneration.from_pretrained(
 ## LlavaOnevisionProcessor
 
 [[autodoc]] LlavaOnevisionProcessor
+    - __call__
 
 ## LlavaOnevisionImageProcessor
 

diff --git a/docs/source/en/model_doc/mllama.md b/docs/source/en/model_doc/mllama.md
@@ -108,6 +108,7 @@ print(processor.decode(output[0], skip_special_tokens=True))
 ## MllamaProcessor
 
 [[autodoc]] MllamaProcessor
+    - __call__
 
 ## MllamaImageProcessor
 

diff --git a/docs/source/en/model_doc/musicgen.md b/docs/source/en/model_doc/musicgen.md
@@ -272,6 +272,7 @@ Tips:
 ## MusicgenProcessor
 
 [[autodoc]] MusicgenProcessor
+    - __call__
 
 ## MusicgenModel
 

diff --git a/docs/source/en/model_doc/musicgen_melody.md b/docs/source/en/model_doc/musicgen_melody.md
@@ -266,6 +266,7 @@ Tips:
 ## MusicgenMelodyProcessor
 
 [[autodoc]] MusicgenMelodyProcessor
+    - __call__
     - get_unconditional_inputs
 
 ## MusicgenMelodyFeatureExtractor

diff --git a/docs/source/en/model_doc/omdet-turbo.md b/docs/source/en/model_doc/omdet-turbo.md
@@ -164,6 +164,7 @@ Detected statue with confidence 0.2 at location [428.1, 205.5, 767.3, 759.5] in
 ## OmDetTurboProcessor
 
 [[autodoc]] OmDetTurboProcessor
+    - __call__
     - post_process_grounded_object_detection
 
 ## OmDetTurboForObjectDetection

diff --git a/docs/source/en/model_doc/oneformer.md b/docs/source/en/model_doc/oneformer.md
@@ -85,6 +85,7 @@ The resource should ideally demonstrate something new instead of duplicating an
 ## OneFormerProcessor
 
 [[autodoc]] OneFormerProcessor
+    - __call__
 
 ## OneFormerModel
 

diff --git a/docs/source/en/model_doc/ovis2.md b/docs/source/en/model_doc/ovis2.md
@@ -107,3 +107,4 @@ with torch.inference_mode():
 ## Ovis2Processor
 
 [[autodoc]] Ovis2Processor
+    - __call__
diff --git a/docs/source/en/model_doc/paddleocr_vl.md b/docs/source/en/model_doc/paddleocr_vl.md
@@ -242,6 +242,7 @@ model = AutoModelForImageTextToText.from_pretrained("PaddlePaddle/PaddleOCR-VL",
 ## PaddleOCRVLProcessor
 
 [[autodoc]] PaddleOCRVLProcessor
+    - __call__
 
 ## PaddleOCRVisionTransformer
 

diff --git a/docs/source/en/model_doc/paligemma.md b/docs/source/en/model_doc/paligemma.md
@@ -175,6 +175,7 @@ visualizer("<img> What is in this image?")
 ## PaliGemmaProcessor
 
 [[autodoc]] PaliGemmaProcessor
+    - __call__
 
 ## PaliGemmaModel
 

diff --git a/docs/source/en/model_doc/perception_lm.md b/docs/source/en/model_doc/perception_lm.md
@@ -48,6 +48,7 @@ The original code can be found [here](https://github.com/facebookresearch/percep
 ## PerceptionLMProcessor
 
 [[autodoc]] PerceptionLMProcessor
+    - __call__
 
 ## PerceptionLMImageProcessorFast
 

diff --git a/docs/source/en/model_doc/phi4_multimodal.md b/docs/source/en/model_doc/phi4_multimodal.md
@@ -152,6 +152,7 @@ print(f'>>> Response\n{response}')
 ## Phi4MultimodalProcessor
 
 [[autodoc]] Phi4MultimodalProcessor
+    - __call__
 
 ## Phi4MultimodalAudioConfig
Original file line number	Diff line number	Diff line change
Expand Up		@@ -126,3 +126,4 @@ for label, prob in zip(labels, probs[0]):
		## AltCLIPProcessor

		[[autodoc]] AltCLIPProcessor
		- __call__
Original file line number	Diff line number	Diff line change
Expand Up		@@ -139,3 +139,4 @@ print(outputs)
		## Cohere2VisionProcessor

		[[autodoc]] Cohere2VisionProcessor
		- __call__
Original file line number	Diff line number	Diff line change
Expand Up		@@ -107,3 +107,4 @@ with torch.inference_mode():
		## Ovis2Processor

		[[autodoc]] Ovis2Processor
		- __call__