diff --git a/docs/source/en/_toctree.yml b/docs/source/en/_toctree.yml
index 5ea5f2359b5..f73ad8e035b 100644
--- a/docs/source/en/_toctree.yml
+++ b/docs/source/en/_toctree.yml
@@ -164,286 +164,301 @@
       title: Feature Extractor
     title: Main Classes
   - sections:
-    - local: model_doc/albert
-      title: ALBERT
     - local: model_doc/auto
       title: Auto Classes
-    - local: model_doc/bart
-      title: BART
-    - local: model_doc/barthez
-      title: BARThez
-    - local: model_doc/bartpho
-      title: BARTpho
-    - local: model_doc/beit
-      title: BEiT
-    - local: model_doc/bert
-      title: BERT
-    - local: model_doc/bert-generation
-      title: BertGeneration
-    - local: model_doc/bert-japanese
-      title: BertJapanese
-    - local: model_doc/bertweet
-      title: Bertweet
-    - local: model_doc/big_bird
-      title: BigBird
-    - local: model_doc/bigbird_pegasus
-      title: BigBirdPegasus
-    - local: model_doc/blenderbot
-      title: Blenderbot
-    - local: model_doc/blenderbot-small
-      title: Blenderbot Small
-    - local: model_doc/bloom
-      title: BLOOM
-    - local: model_doc/bort
-      title: BORT
-    - local: model_doc/byt5
-      title: ByT5
-    - local: model_doc/camembert
-      title: CamemBERT
-    - local: model_doc/canine
-      title: CANINE
-    - local: model_doc/clip
-      title: CLIP
-    - local: model_doc/codegen
-      title: CodeGen
-    - local: model_doc/convbert
-      title: ConvBERT
-    - local: model_doc/convnext
-      title: ConvNeXT
-    - local: model_doc/cpm
-      title: CPM
-    - local: model_doc/ctrl
-      title: CTRL
-    - local: model_doc/cvt
-      title: CvT
-    - local: model_doc/data2vec
-      title: Data2Vec
-    - local: model_doc/deberta
-      title: DeBERTa
-    - local: model_doc/deberta-v2
-      title: DeBERTa-v2
-    - local: model_doc/decision_transformer
-      title: Decision Transformer
-    - local: model_doc/deit
-      title: DeiT
-    - local: model_doc/detr
-      title: DETR
-    - local: model_doc/dialogpt
-      title: DialoGPT
-    - local: model_doc/distilbert
-      title: DistilBERT
-    - local: model_doc/dit
-      title: DiT
-    - local: model_doc/dpr
-      title: DPR
-    - local: model_doc/dpt
-      title: DPT
-    - local: model_doc/electra
-      title: ELECTRA
-    - local: model_doc/encoder-decoder
-      title: Encoder Decoder Models
-    - local: model_doc/flaubert
-      title: FlauBERT
-    - local: model_doc/flava
-      title: FLAVA
-    - local: model_doc/fnet
-      title: FNet
-    - local: model_doc/fsmt
-      title: FSMT
-    - local: model_doc/funnel
-      title: Funnel Transformer
-    - local: model_doc/glpn
-      title: GLPN
-    - local: model_doc/openai-gpt
-      title: GPT
-    - local: model_doc/gpt_neo
-      title: GPT Neo
-    - local: model_doc/gpt_neox
-      title: GPT NeoX
-    - local: model_doc/gptj
-      title: GPT-J
-    - local: model_doc/gpt2
-      title: GPT2
-    - local: model_doc/groupvit
-      title: GroupViT
-    - local: model_doc/herbert
-      title: HerBERT
-    - local: model_doc/hubert
-      title: Hubert
-    - local: model_doc/ibert
-      title: I-BERT
-    - local: model_doc/imagegpt
-      title: ImageGPT
-    - local: model_doc/layoutlm
-      title: LayoutLM
-    - local: model_doc/layoutlmv2
-      title: LayoutLMV2
-    - local: model_doc/layoutlmv3
-      title: LayoutLMV3
-    - local: model_doc/layoutxlm
-      title: LayoutXLM
-    - local: model_doc/led
-      title: LED
-    - local: model_doc/levit
-      title: LeViT
-    - local: model_doc/longformer
-      title: Longformer
-    - local: model_doc/longt5
-      title: LongT5
-    - local: model_doc/luke
-      title: LUKE
-    - local: model_doc/lxmert
-      title: LXMERT
-    - local: model_doc/m2m_100
-      title: M2M100
-    - local: model_doc/marian
-      title: MarianMT
-    - local: model_doc/maskformer
-      title: MaskFormer
-    - local: model_doc/mbart
-      title: MBart and MBart-50
-    - local: model_doc/mctct
-      title: MCTCT
-    - local: model_doc/megatron-bert
-      title: MegatronBERT
-    - local: model_doc/megatron_gpt2
-      title: MegatronGPT2
-    - local: model_doc/mluke
-      title: mLUKE
-    - local: model_doc/mobilebert
-      title: MobileBERT
-    - local: model_doc/mobilevit
-      title: MobileViT
-    - local: model_doc/mpnet
-      title: MPNet
-    - local: model_doc/mt5
-      title: MT5
-    - local: model_doc/mvp
-      title: MVP
-    - local: model_doc/nezha
-      title: NEZHA
-    - local: model_doc/nllb
-      title: NLLB
-    - local: model_doc/nystromformer
-      title: Nyströmformer
-    - local: model_doc/opt
-      title: OPT
-    - local: model_doc/owlvit
-      title: OWL-ViT
-    - local: model_doc/pegasus
-      title: Pegasus
-    - local: model_doc/perceiver
-      title: Perceiver
-    - local: model_doc/phobert
-      title: PhoBERT
-    - local: model_doc/plbart
-      title: PLBart
-    - local: model_doc/poolformer
-      title: PoolFormer
-    - local: model_doc/prophetnet
-      title: ProphetNet
-    - local: model_doc/qdqbert
-      title: QDQBert
-    - local: model_doc/rag
-      title: RAG
-    - local: model_doc/realm
-      title: REALM
-    - local: model_doc/reformer
-      title: Reformer
-    - local: model_doc/regnet
-      title: RegNet
-    - local: model_doc/rembert
-      title: RemBERT
-    - local: model_doc/resnet
-      title: ResNet
-    - local: model_doc/retribert
-      title: RetriBERT
-    - local: model_doc/roberta
-      title: RoBERTa
-    - local: model_doc/roformer
-      title: RoFormer
-    - local: model_doc/segformer
-      title: SegFormer
-    - local: model_doc/sew
-      title: SEW
-    - local: model_doc/sew-d
-      title: SEW-D
-    - local: model_doc/speech-encoder-decoder
-      title: Speech Encoder Decoder Models
-    - local: model_doc/speech_to_text
-      title: Speech2Text
-    - local: model_doc/speech_to_text_2
-      title: Speech2Text2
-    - local: model_doc/splinter
-      title: Splinter
-    - local: model_doc/squeezebert
-      title: SqueezeBERT
-    - local: model_doc/swin
-      title: Swin Transformer
-    - local: model_doc/swinv2
-      title: Swin Transformer V2
-    - local: model_doc/t5
-      title: T5
-    - local: model_doc/t5v1.1
-      title: T5v1.1
-    - local: model_doc/tapas
-      title: TAPAS
-    - local: model_doc/tapex
-      title: TAPEX
-    - local: model_doc/trajectory_transformer
-      title: Trajectory Transformer
-    - local: model_doc/transfo-xl
-      title: Transformer XL
-    - local: model_doc/trocr
-      title: TrOCR
-    - local: model_doc/ul2
-      title: UL2
-    - local: model_doc/unispeech
-      title: UniSpeech
-    - local: model_doc/unispeech-sat
-      title: UniSpeech-SAT
-    - local: model_doc/van
-      title: VAN
-    - local: model_doc/vilt
-      title: ViLT
-    - local: model_doc/vision-encoder-decoder
-      title: Vision Encoder Decoder Models
-    - local: model_doc/vision-text-dual-encoder
-      title: Vision Text Dual Encoder
-    - local: model_doc/vit
-      title: Vision Transformer (ViT)
-    - local: model_doc/visual_bert
-      title: VisualBERT
-    - local: model_doc/vit_mae
-      title: ViTMAE
-    - local: model_doc/wav2vec2
-      title: Wav2Vec2
-    - local: model_doc/wav2vec2-conformer
-      title: Wav2Vec2-Conformer
-    - local: model_doc/wav2vec2_phoneme
-      title: Wav2Vec2Phoneme
-    - local: model_doc/wavlm
-      title: WavLM
-    - local: model_doc/xglm
-      title: XGLM
-    - local: model_doc/xlm
-      title: XLM
-    - local: model_doc/xlm-prophetnet
-      title: XLM-ProphetNet
-    - local: model_doc/xlm-roberta
-      title: XLM-RoBERTa
-    - local: model_doc/xlm-roberta-xl
-      title: XLM-RoBERTa-XL
-    - local: model_doc/xlnet
-      title: XLNet
-    - local: model_doc/xls_r
-      title: XLS-R
-    - local: model_doc/xlsr_wav2vec2
-      title: XLSR-Wav2Vec2
-    - local: model_doc/yolos
-      title: YOLOS
-    - local: model_doc/yoso
-      title: YOSO
+    - isExpanded: false
+      sections:
+      - local: model_doc/albert
+        title: ALBERT
+      - local: model_doc/bart
+        title: BART
+      - local: model_doc/barthez
+        title: BARThez
+      - local: model_doc/bartpho
+        title: BARTpho
+      - local: model_doc/bert
+        title: BERT
+      - local: model_doc/bert-generation
+        title: BertGeneration
+      - local: model_doc/bert-japanese
+        title: BertJapanese
+      - local: model_doc/bertweet
+        title: Bertweet
+      - local: model_doc/big_bird
+        title: BigBird
+      - local: model_doc/bigbird_pegasus
+        title: BigBirdPegasus
+      - local: model_doc/blenderbot
+        title: Blenderbot
+      - local: model_doc/blenderbot-small
+        title: Blenderbot Small
+      - local: model_doc/bloom
+        title: BLOOM
+      - local: model_doc/bort
+        title: BORT
+      - local: model_doc/byt5
+        title: ByT5
+      - local: model_doc/camembert
+        title: CamemBERT
+      - local: model_doc/canine
+        title: CANINE
+      - local: model_doc/codegen
+        title: CodeGen
+      - local: model_doc/convbert
+        title: ConvBERT
+      - local: model_doc/cpm
+        title: CPM
+      - local: model_doc/ctrl
+        title: CTRL
+      - local: model_doc/deberta
+        title: DeBERTa
+      - local: model_doc/deberta-v2
+        title: DeBERTa-v2
+      - local: model_doc/dialogpt
+        title: DialoGPT
+      - local: model_doc/distilbert
+        title: DistilBERT
+      - local: model_doc/dpr
+        title: DPR
+      - local: model_doc/electra
+        title: ELECTRA
+      - local: model_doc/encoder-decoder
+        title: Encoder Decoder Models
+      - local: model_doc/flaubert
+        title: FlauBERT
+      - local: model_doc/fnet
+        title: FNet
+      - local: model_doc/fsmt
+        title: FSMT
+      - local: model_doc/funnel
+        title: Funnel Transformer
+      - local: model_doc/openai-gpt
+        title: GPT
+      - local: model_doc/gpt_neo
+        title: GPT Neo
+      - local: model_doc/gpt_neox
+        title: GPT NeoX
+      - local: model_doc/gptj
+        title: GPT-J
+      - local: model_doc/gpt2
+        title: GPT2
+      - local: model_doc/herbert
+        title: HerBERT
+      - local: model_doc/ibert
+        title: I-BERT
+      - local: model_doc/layoutlm
+        title: LayoutLM
+      - local: model_doc/led
+        title: LED
+      - local: model_doc/longformer
+        title: Longformer
+      - local: model_doc/longt5
+        title: LongT5
+      - local: model_doc/luke
+        title: LUKE
+      - local: model_doc/lxmert
+        title: LXMERT
+      - local: model_doc/m2m_100
+        title: M2M100
+      - local: model_doc/marian
+        title: MarianMT
+      - local: model_doc/mbart
+        title: MBart and MBart-50
+      - local: model_doc/megatron-bert
+        title: MegatronBERT
+      - local: model_doc/megatron_gpt2
+        title: MegatronGPT2
+      - local: model_doc/mluke
+        title: mLUKE
+      - local: model_doc/mobilebert
+        title: MobileBERT
+      - local: model_doc/mpnet
+        title: MPNet
+      - local: model_doc/mt5
+        title: MT5
+      - local: model_doc/mvp
+        title: MVP
+      - local: model_doc/nezha
+        title: NEZHA
+      - local: model_doc/nllb
+        title: NLLB
+      - local: model_doc/nystromformer
+        title: Nyströmformer
+      - local: model_doc/opt
+        title: OPT
+      - local: model_doc/pegasus
+        title: Pegasus
+      - local: model_doc/phobert
+        title: PhoBERT
+      - local: model_doc/plbart
+        title: PLBart
+      - local: model_doc/prophetnet
+        title: ProphetNet
+      - local: model_doc/qdqbert
+        title: QDQBert
+      - local: model_doc/rag
+        title: RAG
+      - local: model_doc/realm
+        title: REALM
+      - local: model_doc/reformer
+        title: Reformer
+      - local: model_doc/rembert
+        title: RemBERT
+      - local: model_doc/retribert
+        title: RetriBERT
+      - local: model_doc/roberta
+        title: RoBERTa
+      - local: model_doc/roformer
+        title: RoFormer
+      - local: model_doc/splinter
+        title: Splinter
+      - local: model_doc/squeezebert
+        title: SqueezeBERT
+      - local: model_doc/t5
+        title: T5
+      - local: model_doc/t5v1.1
+        title: T5v1.1
+      - local: model_doc/tapas
+        title: TAPAS
+      - local: model_doc/tapex
+        title: TAPEX
+      - local: model_doc/transfo-xl
+        title: Transformer XL
+      - local: model_doc/ul2
+        title: UL2
+      - local: model_doc/xglm
+        title: XGLM
+      - local: model_doc/xlm
+        title: XLM
+      - local: model_doc/xlm-prophetnet
+        title: XLM-ProphetNet
+      - local: model_doc/xlm-roberta
+        title: XLM-RoBERTa
+      - local: model_doc/xlm-roberta-xl
+        title: XLM-RoBERTa-XL
+      - local: model_doc/xlnet
+        title: XLNet
+      - local: model_doc/yoso
+        title: YOSO
+      title: Text models
+    - isExpanded: false
+      sections:
+      - local: model_doc/beit
+        title: BEiT
+      - local: model_doc/convnext
+        title: ConvNeXT
+      - local: model_doc/cvt
+        title: CvT
+      - local: model_doc/deit
+        title: DeiT
+      - local: model_doc/detr
+        title: DETR
+      - local: model_doc/dit
+        title: DiT
+      - local: model_doc/dpt
+        title: DPT
+      - local: model_doc/glpn
+        title: GLPN
+      - local: model_doc/groupvit
+        title: GroupViT
+      - local: model_doc/imagegpt
+        title: ImageGPT
+      - local: model_doc/levit
+        title: LeViT
+      - local: model_doc/maskformer
+        title: MaskFormer
+      - local: model_doc/mobilevit
+        title: MobileViT
+      - local: model_doc/owlvit
+        title: OWL-ViT
+      - local: model_doc/poolformer
+        title: PoolFormer
+      - local: model_doc/regnet
+        title: RegNet
+      - local: model_doc/resnet
+        title: ResNet
+      - local: model_doc/segformer
+        title: SegFormer
+      - local: model_doc/swin
+        title: Swin Transformer
+      - local: model_doc/swinv2
+        title: Swin Transformer V2
+      - local: model_doc/van
+        title: VAN
+      - local: model_doc/vit
+        title: Vision Transformer (ViT)
+      - local: model_doc/vit_mae
+        title: ViTMAE
+      - local: model_doc/yolos
+        title: YOLOS
+      title: Vision models
+    - isExpanded: false
+      sections:
+      - local: model_doc/hubert
+        title: Hubert
+      - local: model_doc/mctct
+        title: MCTCT
+      - local: model_doc/sew
+        title: SEW
+      - local: model_doc/sew-d
+        title: SEW-D
+      - local: model_doc/speech_to_text
+        title: Speech2Text
+      - local: model_doc/speech_to_text_2
+        title: Speech2Text2
+      - local: model_doc/unispeech
+        title: UniSpeech
+      - local: model_doc/unispeech-sat
+        title: UniSpeech-SAT
+      - local: model_doc/wav2vec2
+        title: Wav2Vec2
+      - local: model_doc/wav2vec2-conformer
+        title: Wav2Vec2-Conformer
+      - local: model_doc/wav2vec2_phoneme
+        title: Wav2Vec2Phoneme
+      - local: model_doc/wavlm
+        title: WavLM
+      - local: model_doc/xls_r
+        title: XLS-R
+      - local: model_doc/xlsr_wav2vec2
+        title: XLSR-Wav2Vec2
+      title: Audio models
+    - isExpanded: false
+      sections:
+      - local: model_doc/clip
+        title: CLIP
+      - local: model_doc/data2vec
+        title: Data2Vec
+      - local: model_doc/flava
+        title: FLAVA
+      - local: model_doc/layoutlmv2
+        title: LayoutLMV2
+      - local: model_doc/layoutlmv3
+        title: LayoutLMV3
+      - local: model_doc/layoutxlm
+        title: LayoutXLM
+      - local: model_doc/perceiver
+        title: Perceiver
+      - local: model_doc/speech-encoder-decoder
+        title: Speech Encoder Decoder Models
+      - local: model_doc/trocr
+        title: TrOCR
+      - local: model_doc/vilt
+        title: ViLT
+      - local: model_doc/vision-encoder-decoder
+        title: Vision Encoder Decoder Models
+      - local: model_doc/vision-text-dual-encoder
+        title: Vision Text Dual Encoder
+      - local: model_doc/visual_bert
+        title: VisualBERT
+      title: Multimodal models
+    - isExpanded: false
+      sections:
+      - local: model_doc/decision_transformer
+        title: Decision Transformer
+      - local: model_doc/trajectory_transformer
+        title: Trajectory Transformer
+      title: Reinforcement learning models
     title: Models
   - sections:
     - local: internal/modeling_utils
diff --git a/utils/check_doc_toc.py b/utils/check_doc_toc.py
index ae0389d60f0..67ec2f94660 100644
--- a/utils/check_doc_toc.py
+++ b/utils/check_doc_toc.py
@@ -65,12 +65,22 @@ def check_model_doc(overwrite=False):
     while api_doc[model_idx]["title"] != "Models":
         model_idx += 1
 
-    old_model_doc = api_doc[model_idx]["sections"]
-    new_model_doc = clean_model_doc_toc(old_model_doc)
+    model_doc = api_doc[model_idx]["sections"]
 
-    if old_model_doc != new_model_doc:
+    modalities_docs = [(idx, section) for idx, section in enumerate(model_doc) if "sections" in section]
+    diff = False
+    for idx, modality_doc in modalities_docs:
+        old_modality_doc = modality_doc["sections"]
+        new_modality_doc = clean_model_doc_toc(old_modality_doc)
+
+        if old_modality_doc != new_modality_doc:
+            diff = True
+            if overwrite:
+                model_doc[idx]["sections"] = new_modality_doc
+
+    if diff:
         if overwrite:
-            api_doc[model_idx]["sections"] = new_model_doc
+            api_doc[model_idx]["sections"] = model_doc
             content[api_idx]["sections"] = api_doc
             with open(PATH_TO_TOC, "w", encoding="utf-8") as f:
                 f.write(yaml.dump(content, allow_unicode=True))