Spaces:
Sleeping
Sleeping
| local: model_doc/vit | |
| title: Vision Transformer (ViT) | |
| local: model_doc/vit_hybrid | |
| title: ViT Hybrid | |
| local: model_doc/vitdet | |
| title: ViTDet | |
| local: model_doc/vit_mae | |
| title: ViTMAE | |
| local: model_doc/vitmatte | |
| title: ViTMatte | |
| local: model_doc/vit_msn | |
| title: ViTMSN | |
| local: model_doc/yolos | |
| title: YOLOS | |
| title: Vision models | |
| isExpanded: false | |
| sections: | |
| local: model_doc/audio-spectrogram-transformer | |
| title: Audio Spectrogram Transformer | |
| local: model_doc/bark | |
| title: Bark | |
| local: model_doc/clap | |
| title: CLAP | |
| local: model_doc/encodec | |
| title: EnCodec | |
| local: model_doc/hubert | |
| title: Hubert | |
| local: model_doc/mctct | |
| title: MCTCT | |
| local: model_doc/mms | |
| title: MMS | |
| local: model_doc/musicgen | |
| title: MusicGen | |
| local: model_doc/musicgen_melody | |
| title: MusicGen Melody | |
| local: model_doc/pop2piano | |
| title: Pop2Piano | |
| local: model_doc/seamless_m4t | |
| title: Seamless-M4T | |
| local: model_doc/seamless_m4t_v2 | |
| title: SeamlessM4T-v2 | |
| 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/speecht5 | |
| title: SpeechT5 | |
| local: model_doc/unispeech | |
| title: UniSpeech | |
| local: model_doc/unispeech-sat | |
| title: UniSpeech-SAT | |
| local: model_doc/univnet | |
| title: UnivNet | |
| local: model_doc/vits | |
| title: VITS | |
| local: model_doc/wav2vec2 | |
| title: Wav2Vec2 | |
| local: model_doc/wav2vec2-bert | |
| title: Wav2Vec2-BERT | |
| local: model_doc/wav2vec2-conformer | |
| title: Wav2Vec2-Conformer | |
| local: model_doc/wav2vec2_phoneme | |
| title: Wav2Vec2Phoneme | |
| local: model_doc/wavlm | |
| title: WavLM | |
| local: model_doc/whisper | |
| title: Whisper | |
| 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/timesformer | |
| title: TimeSformer | |
| local: model_doc/videomae | |
| title: VideoMAE | |
| local: model_doc/vivit | |
| title: ViViT | |
| title: Video models | |
| isExpanded: false | |
| sections: | |
| local: model_doc/align | |
| title: ALIGN | |
| local: model_doc/altclip | |
| title: AltCLIP | |
| local: model_doc/blip | |
| title: BLIP | |
| local: model_doc/blip-2 | |
| title: BLIP-2 | |
| local: model_doc/bridgetower | |
| title: BridgeTower | |
| local: model_doc/bros | |
| title: BROS | |
| local: model_doc/chinese_clip | |
| title: Chinese-CLIP | |
| local: model_doc/clip | |
| title: CLIP | |
| local: model_doc/clipseg | |
| title: CLIPSeg | |
| local: model_doc/clvp | |
| title: CLVP | |
| local: model_doc/data2vec | |
| title: Data2Vec | |
| local: model_doc/deplot | |
| title: DePlot | |
| local: model_doc/donut | |
| title: Donut | |
| local: model_doc/flava | |
| title: FLAVA | |
| local: model_doc/git | |
| title: GIT | |
| local: model_doc/grounding-dino | |
| title: Grounding DINO | |
| local: model_doc/groupvit | |
| title: GroupViT | |
| local: model_doc/idefics | |
| title: IDEFICS | |
| local: model_doc/idefics2 | |
| title: Idefics2 | |
| local: model_doc/instructblip | |
| title: InstructBLIP | |
| local: model_doc/kosmos-2 | |
| title: KOSMOS-2 | |
| local: model_doc/layoutlm |