[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"cat-audio":3,"cat-models-audio":100},[4,14,22,29,37,44,51,58,65,72,80,88,94],{"slug":5,"name":6,"description":7,"model_count":8,"priority":9,"seo":10},"video-generation","视频生成","Text\u002Fimage to video generation models",10,1,{"title":11,"description":7,"image":12,"robots":13,"canonical_url":12},"视频生成 Models",null,"index, follow",{"slug":15,"name":16,"description":17,"model_count":18,"priority":19,"seo":20},"video-understanding","Video Understanding","Video → Text \u002F Summary \u002F Events \u002F Caption \u002F Search",0,2,{"title":21,"description":17,"image":12,"robots":13,"canonical_url":12},"Video Understanding Models",{"slug":23,"name":24,"description":25,"model_count":26,"priority":19,"seo":27},"image-generation","图像生成","Text to image diffusion models",6,{"title":28,"description":25,"image":12,"robots":13,"canonical_url":12},"图像生成 Models",{"slug":30,"name":31,"description":32,"model_count":33,"priority":34,"seo":35},"llm","大语言模型","Large language models and chat models",327,3,{"title":36,"description":32,"image":12,"robots":13,"canonical_url":12},"大语言模型 Models",{"slug":38,"name":39,"description":40,"model_count":18,"priority":41,"seo":42},"vlm","Vision \u002F VLM","Vision-Language models: image+text understanding",4,{"title":43,"description":40,"image":12,"robots":13,"canonical_url":12},"Vision \u002F VLM Models",{"slug":45,"name":46,"description":47,"model_count":48,"priority":41,"seo":49},"coding","代码 AI","Code generation and completion models",46,{"title":50,"description":47,"image":12,"robots":13,"canonical_url":12},"代码 AI Models",{"slug":52,"name":53,"description":54,"model_count":18,"priority":55,"seo":56},"agent","AI 智能体","Agentic and tool-use models",5,{"title":57,"description":54,"image":12,"robots":13,"canonical_url":12},"AI 智能体 Models",{"slug":59,"name":60,"description":61,"model_count":62,"priority":26,"seo":63},"audio","语音","Speech recognition and synthesis",14,{"title":64,"description":61,"image":12,"robots":13,"canonical_url":12},"语音 Models",{"slug":66,"name":67,"description":68,"model_count":26,"priority":69,"seo":70},"translation","翻译","Machine translation models",7,{"title":71,"description":68,"image":12,"robots":13,"canonical_url":12},"翻译 Models",{"slug":73,"name":74,"description":75,"model_count":76,"priority":77,"seo":78},"ocr-vision","OCR \u002F 视觉","Optical character recognition and vision",40,8,{"title":79,"description":75,"image":12,"robots":13,"canonical_url":12},"OCR \u002F 视觉 Models",{"slug":81,"name":82,"description":83,"model_count":84,"priority":85,"seo":86},"embedding","向量 \u002F RAG","Text embedding and retrieval models",18,9,{"title":87,"description":83,"image":12,"robots":13,"canonical_url":12},"向量 \u002F RAG Models",{"slug":89,"name":90,"description":91,"model_count":18,"priority":85,"seo":92},"3d-generation","3D Generation","Text\u002FImage → 3D models and scenes",{"title":93,"description":91,"image":12,"robots":13,"canonical_url":12},"3D Generation Models",{"slug":95,"name":96,"description":97,"model_count":18,"priority":8,"seo":98},"avatar","Avatar \u002F Digital Human","Digital human, talking head, lip-sync, virtual avatar",{"title":99,"description":97,"image":12,"robots":13,"canonical_url":12},"Avatar \u002F Digital Human Models",[101,111,121,129,137,148,158,165,174,183,190,201,213,225],{"id":102,"slug":103,"name":104,"hf_id":104,"organization":105,"parameters_label":106,"parameters":107,"context_length":12,"downloads":108,"likes":109,"license":12,"description":12,"category":59,"family":105,"trend_score":110},451,"kokoro-82m","hexgrad\u002FKokoro-82M","hexgrad","82M",82000000,11982890,6689,0.0989,{"id":112,"slug":113,"name":114,"hf_id":114,"organization":115,"parameters_label":116,"parameters":12,"context_length":12,"downloads":117,"likes":118,"license":12,"description":12,"category":59,"family":119,"trend_score":120},469,"whisperkit-coreml","argmaxinc\u002Fwhisperkit-coreml","argmaxinc","0",9171662,200,"whisper",0.0166,{"id":122,"slug":123,"name":124,"hf_id":124,"organization":125,"parameters_label":116,"parameters":12,"context_length":12,"downloads":126,"likes":127,"license":12,"description":12,"category":59,"family":125,"trend_score":128},468,"speaker-diarization-3-1","pyannote\u002Fspeaker-diarization-3.1","pyannote",9075594,3059,0.052,{"id":130,"slug":131,"name":132,"hf_id":132,"organization":133,"parameters_label":116,"parameters":12,"context_length":12,"downloads":134,"likes":135,"license":12,"description":12,"category":59,"family":133,"trend_score":136},471,"xtts-v2","coqui\u002FXTTS-v2","coqui",8660087,3730,0.0548,{"id":138,"slug":139,"name":140,"hf_id":140,"organization":141,"parameters_label":142,"parameters":143,"context_length":12,"downloads":144,"likes":145,"license":12,"description":12,"category":59,"family":146,"trend_score":147},475,"whisper-large-v3-turbo","openai\u002Fwhisper-large-v3-turbo","openai","808.9M",808878080,7912990,3238,"yi",0.0841,{"id":149,"slug":150,"name":151,"hf_id":151,"organization":152,"parameters_label":153,"parameters":154,"context_length":12,"downloads":155,"likes":156,"license":12,"description":12,"category":59,"family":152,"trend_score":157},484,"wav2vec2-large-xlsr-53-japanese","jonatasgrosman\u002Fwav2vec2-large-xlsr-53-japanese","jonatasgrosman","304.4M",304387072,5787919,62,0.0178,{"id":159,"slug":160,"name":161,"hf_id":161,"organization":125,"parameters_label":116,"parameters":12,"context_length":12,"downloads":162,"likes":163,"license":12,"description":12,"category":59,"family":125,"trend_score":164},487,"speaker-diarization-community-1","pyannote\u002Fspeaker-diarization-community-1",5463773,1016,0.0614,{"id":76,"slug":166,"name":167,"hf_id":167,"organization":141,"parameters_label":168,"parameters":169,"context_length":12,"downloads":170,"likes":171,"license":12,"description":172,"category":59,"family":146,"trend_score":173},"whisper-large-v3","openai\u002Fwhisper-large-v3","1.5B",1543490560,5013186,6147,"Whisper large-v3 顶级语音识别。",0.0758,{"id":175,"slug":176,"name":177,"hf_id":177,"organization":152,"parameters_label":178,"parameters":179,"context_length":12,"downloads":180,"likes":181,"license":12,"description":12,"category":59,"family":152,"trend_score":182},490,"wav2vec2-large-xlsr-53-portuguese","jonatasgrosman\u002Fwav2vec2-large-xlsr-53-portuguese","302M",302036992,4886538,55,0.0083,{"id":184,"slug":185,"name":186,"hf_id":186,"organization":125,"parameters_label":116,"parameters":12,"context_length":12,"downloads":187,"likes":188,"license":12,"description":12,"category":59,"family":125,"trend_score":189},509,"voice-activity-detection","pyannote\u002Fvoice-activity-detection",4132780,240,0.0305,{"id":191,"slug":192,"name":193,"hf_id":193,"organization":194,"parameters_label":195,"parameters":196,"context_length":12,"downloads":197,"likes":198,"license":12,"description":12,"category":59,"family":199,"trend_score":200},507,"qwen3-asr-0-6b","Qwen\u002FQwen3-ASR-0.6B","Qwen","938M",938008576,4123784,330,"qwen",0.0101,{"id":202,"slug":203,"name":203,"hf_id":204,"organization":205,"parameters_label":168,"parameters":206,"context_length":207,"downloads":208,"likes":209,"license":210,"description":211,"category":59,"family":119,"trend_score":212},41,"faster-whisper-large-v3","Systran\u002Ffaster-whisper-large-v3","Systran",1500000000,448,2200000,2900,"Apache-2.0","CTranslate2 优化版 Whisper，推理快 4 倍。",0.1259,{"id":214,"slug":215,"name":216,"hf_id":217,"organization":194,"parameters_label":218,"parameters":219,"context_length":220,"downloads":221,"likes":222,"license":223,"description":12,"category":59,"family":199,"trend_score":224},328,"qwen2-audio-7b","Qwen2-Audio 7B","Qwen\u002FQwen2-Audio-7B-Instruct","7.6B",7600000000,8192,607914,551,"MIT",0.007,{"id":226,"slug":227,"name":228,"hf_id":229,"organization":230,"parameters_label":231,"parameters":232,"context_length":233,"downloads":234,"likes":235,"license":223,"description":12,"category":59,"family":12,"trend_score":236},391,"voxtral-small-24b","Voxtral Small 24B","mistralai\u002FVoxtral-Small-24B-2507","mistralai","24B",24000000000,32768,245801,519,0.0061]