AnyAccomp
Generalizable Accompaniment Generation
The North-Star objective of Amphion is to offer a platform for studying the conversion of any inputs into audio. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development. Amphion offers a unique feature: visualizations of classic models or architectures. We believe that these visualizations are beneficial for junior researchers and engineers who wish to gain a better understanding of the model.
\nTechnical Report: https://huggingface.co/papers/2312.09911
\nDiscord: https://discord.com/invite/ZxxREr3Y
\n","classNames":"hf-sanitized hf-sanitized-u0x_8qMs_BtGiIhRwZ8y1"},"users":[{"_id":"63b4dcefa50cfcefdaa121f3","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63b4dcefa50cfcefdaa121f3/MlIxOaTSCbZARVyo8Ly7r.jpeg","isPro":false,"fullname":"Dr Wuz","user":"drwuz","type":"user"},{"_id":"60486b2cec955c4994bb6249","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/qNHSGbTA7svVWEO3BI3M7.jpeg","isPro":false,"fullname":"Xueyao Zhang","user":"RMSnow","type":"user"},{"_id":"6290e961473e457463a53248","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6290e961473e457463a53248/-58Dp5uHvdjs9yOupAMs0.jpeg","isPro":true,"fullname":"Liumeng Xue","user":"lmxue","type":"user"},{"_id":"656558f04914c4787126edf6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/656558f04914c4787126edf6/EEO8t_qbTtvDymuAx8NFe.jpeg","isPro":false,"fullname":"Zou Lexiao","user":"Lokshaw","type":"user"},{"_id":"63072d60cd148dbc5e49f4dd","avatarUrl":"/avatars/ffa61038c0ff20848fbcde7c1c34570e.svg","isPro":false,"fullname":"Yuancheng Wang","user":"Hecheng0625","type":"user"},{"_id":"656eb03d228bbe9eb46f163d","avatarUrl":"/avatars/47b75f913a40e22f178b62eaea5272d4.svg","isPro":false,"fullname":"YichengGu","user":"Setsugesuka","type":"user"},{"_id":"6516db25493fe76b259d81d5","avatarUrl":"/avatars/0fed459faddf0bfbf1d290b442197fe5.svg","isPro":false,"fullname":"Tang Tze Ying","user":"zyingt","type":"user"},{"_id":"61a7569eaf0333e76eb428a8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/61a7569eaf0333e76eb428a8/zwseNheR4Hx0DtCmf_v5H.jpeg","isPro":false,"fullname":"HarryHe11","user":"HarryHe","type":"user"},{"_id":"6580349d9aee950d4a8aa134","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/cMXAUckwqGm01K28Oxb1w.png","isPro":false,"fullname":"Zihao Fang","user":"WelkinFang","type":"user"},{"_id":"63f8979cb0ae1748524be22c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1677236096253-noauth.png","isPro":false,"fullname":"junan zhang","user":"viewfinder-annn","type":"user"},{"_id":"657fdd6b42fc53e18b89b856","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/657fdd6b42fc53e18b89b856/kAPLFmH7Bq8WwE3hhDb9H.jpeg","isPro":false,"fullname":"Chaoren Wang","user":"yuantuo666","type":"user"},{"_id":"663023917cff1537e3e8d494","avatarUrl":"/avatars/fc58113e540708dc348456e6ddd6a116.svg","isPro":false,"fullname":"Xiaoyu Zhang","user":"Billpai","type":"user"},{"_id":"662370b1ffe1be5ef3eb73ca","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/662370b1ffe1be5ef3eb73ca/KT1L_Ps60u5cF2y9jM0lS.jpeg","isPro":false,"fullname":"Junyi Ao","user":"ajyyy","type":"user"},{"_id":"6635a711a5243c9638f5e4df","avatarUrl":"/avatars/08651622fc1fd5089551b510be8c4530.svg","isPro":false,"fullname":"Jiaqi Li","user":"jiaqili3","type":"user"},{"_id":"64ca3251710645aa7bd1ccdc","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64ca3251710645aa7bd1ccdc/iQV8f8gU220ECxIkTkea0.jpeg","isPro":false,"fullname":"Zeyu Xie","user":"ZeyuXie","type":"user"},{"_id":"6658798231baf30dc75c3dc4","avatarUrl":"/avatars/db6b6afa5eabde9c7780ef50555220d9.svg","isPro":false,"fullname":"QIao","user":"Qiao111111","type":"user"},{"_id":"6423f6a630b0e4ab36dda350","avatarUrl":"/avatars/678cc5352bf2cf2101e5d3a65446fc8c.svg","isPro":false,"fullname":"hrq","user":"michaelhe","type":"user"},{"_id":"67192660061a8291f7c3c012","avatarUrl":"/avatars/24fc46f33bd0019f251a562ce28ac0a7.svg","isPro":false,"fullname":"zjc","user":"zjc1617018","type":"user"},{"_id":"65c2d05a47ac0454b6527989","avatarUrl":"/avatars/7a8f46b2fd76757bf9e75a9ca2600046.svg","isPro":false,"fullname":"Yonghui Rao","user":"raoyonghui","type":"user"},{"_id":"657fd3c91ede8a7bb7108676","avatarUrl":"/avatars/b5c657c36ba9d3c7ee2606588677499a.svg","isPro":false,"fullname":"Wang Li","user":"wli3221134","type":"user"},{"_id":"67d2a917e8c96134d62a983a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/67d2a917e8c96134d62a983a/z7VK8hsN7FU-yIqTxjypY.png","isPro":false,"fullname":"Hitomi Tee Jin Ling","user":"hitomitee","type":"user"},{"_id":"6661d1795b20b6180097ab45","avatarUrl":"/avatars/da1864d052c7d1ec921cb21f080f515c.svg","isPro":false,"fullname":"Zhekai Li","user":"Mira1sen","type":"user"},{"_id":"644dbbe4ce3065fb76c48bbb","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/644dbbe4ce3065fb76c48bbb/qN3vGfNbMVPyMTXF6yLFP.jpeg","isPro":false,"fullname":"Difficult-Burger","user":"Difficult-Burger","type":"user"},{"_id":"6437a095e282b4a48eada089","avatarUrl":"/avatars/7337e10089b037a1e66f92d79a660399.svg","isPro":false,"fullname":"Tao Feng","user":"Fengt","type":"user"},{"_id":"682469616f0d91769b57340f","avatarUrl":"/avatars/fa8b63d0bfb347cab78940f74a5ba43e.svg","isPro":false,"fullname":"Ge","user":"Zirui12","type":"user"},{"_id":"64dedc82e44c1c0fa8de391d","avatarUrl":"/avatars/0dd9601633ba4ac8fda819e41732fb7c.svg","isPro":false,"fullname":"Hannie","user":"Hannie0813","type":"user"},{"_id":"67b88f317556966023650f36","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/Hh5OTn0KrH2cFQcMLEhi2.png","isPro":true,"fullname":"Yingda Shen","user":"VincentShen","type":"user"},{"_id":"677888fe195b961b77144d41","avatarUrl":"/avatars/ededb94dc60b5f1a2b26b37c918bea6f.svg","isPro":false,"fullname":"Qinke Ni","user":"CharlesNi","type":"user"}],"userCount":28,"collections":[],"datasets":[{"author":"amphion","downloads":11,"gated":"auto","id":"amphion/AdvSV2.0","lastModified":"2026-01-12T09:51:42.000Z","private":false,"repoType":"dataset","likes":1,"isLikedByUser":false,"isBenchmark":false},{"author":"amphion","downloads":5,"gated":false,"id":"amphion/GenTrace","lastModified":"2026-01-05T08:14:34.000Z","private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false},{"author":"amphion","downloads":135,"gated":false,"id":"amphion/SingVERSE","lastModified":"2025-09-29T14:38:41.000Z","datasetsServerInfo":{"viewer":"preview","numRows":0,"libraries":[],"formats":[],"modalities":[]},"private":false,"repoType":"dataset","likes":5,"isLikedByUser":false,"isBenchmark":false},{"author":"amphion","downloads":116,"gated":"auto","id":"amphion/Emilia-NV","lastModified":"2025-09-18T06:19:01.000Z","datasetsServerInfo":{"viewer":"viewer-partial","numRows":173715,"libraries":["datasets","webdataset","mlcroissant"],"formats":["webdataset"],"modalities":["audio","text"]},"private":false,"repoType":"dataset","likes":35,"isLikedByUser":false,"isBenchmark":false},{"author":"amphion","downloads":88,"gated":"auto","id":"amphion/Emilia","lastModified":"2025-09-03T16:32:12.000Z","datasetsServerInfo":{"viewer":"preview","numRows":0,"libraries":[],"formats":[],"modalities":[]},"private":false,"repoType":"dataset","likes":86,"isLikedByUser":false,"isBenchmark":false},{"author":"amphion","downloads":16,"gated":"auto","id":"amphion/INTP","lastModified":"2025-07-28T15:05:43.000Z","datasetsServerInfo":{"viewer":"viewer-partial","numRows":138457,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["audio","text"]},"private":false,"repoType":"dataset","likes":10,"isLikedByUser":false,"isBenchmark":false},{"author":"amphion","downloads":153,"gated":false,"id":"amphion/Amphion-TTS-Eval","lastModified":"2025-05-27T10:22:43.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":8084,"libraries":["datasets","mlcroissant"],"formats":["audiofolder"],"modalities":["audio"]},"private":false,"repoType":"dataset","likes":2,"isLikedByUser":false,"isBenchmark":false},{"author":"amphion","downloads":20,"gated":"manual","id":"amphion/SolidStateBusComp","lastModified":"2025-04-13T12:27:19.000Z","private":false,"repoType":"dataset","likes":2,"isLikedByUser":false,"isBenchmark":false},{"author":"amphion","downloads":58470,"gated":"auto","id":"amphion/Emilia-Dataset","lastModified":"2025-02-28T05:41:37.000Z","datasetsServerInfo":{"viewer":"viewer-partial","numRows":54792590,"libraries":["datasets","webdataset","mlcroissant"],"formats":["webdataset"],"modalities":["audio","text"]},"private":false,"repoType":"dataset","likes":432,"isLikedByUser":false,"isBenchmark":false},{"author":"amphion","downloads":124,"gated":false,"id":"amphion/spmis","lastModified":"2024-11-29T07:50:09.000Z","private":false,"repoType":"dataset","likes":1,"isLikedByUser":false,"isBenchmark":false}],"models":[{"author":"amphion","authorData":{"_id":"6562a925a72f05d2eaac5687","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","fullname":"Amphion","name":"amphion","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":408,"isUserFollowing":false},"downloads":2,"gated":false,"id":"amphion/anyaccomp","availableInferenceProviders":[],"lastModified":"2025-12-22T11:52:36.000Z","likes":7,"private":false,"repoType":"model","isLikedByUser":false},{"author":"amphion","authorData":{"_id":"6562a925a72f05d2eaac5687","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","fullname":"Amphion","name":"amphion","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":408,"isUserFollowing":false},"downloads":0,"gated":false,"id":"amphion/dualcodec","availableInferenceProviders":[],"lastModified":"2025-10-13T16:18:54.000Z","likes":8,"pipeline_tag":"audio-to-audio","private":false,"repoType":"model","isLikedByUser":false},{"author":"amphion","authorData":{"_id":"6562a925a72f05d2eaac5687","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","fullname":"Amphion","name":"amphion","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":408,"isUserFollowing":false},"downloads":0,"gated":"auto","id":"amphion/INTP","availableInferenceProviders":[],"lastModified":"2025-09-08T22:19:08.000Z","likes":0,"private":false,"repoType":"model","isLikedByUser":false},{"author":"amphion","authorData":{"_id":"6562a925a72f05d2eaac5687","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","fullname":"Amphion","name":"amphion","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":408,"isUserFollowing":false},"downloads":27,"gated":false,"id":"amphion/TaDiCodec","availableInferenceProviders":[],"lastModified":"2025-09-02T07:25:21.000Z","likes":27,"pipeline_tag":"audio-to-audio","private":false,"repoType":"model","isLikedByUser":false,"numParameters":499964061},{"author":"amphion","authorData":{"_id":"6562a925a72f05d2eaac5687","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","fullname":"Amphion","name":"amphion","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":408,"isUserFollowing":false},"downloads":4,"gated":false,"id":"amphion/TaDiCodec-TTS-MGM","availableInferenceProviders":[],"lastModified":"2025-09-02T07:25:02.000Z","likes":3,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false,"numParameters":582815744},{"author":"amphion","authorData":{"_id":"6562a925a72f05d2eaac5687","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","fullname":"Amphion","name":"amphion","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":408,"isUserFollowing":false},"downloads":5,"gated":false,"id":"amphion/TaDiCodec-TTS-AR-Qwen2.5-0.5B","availableInferenceProviders":[],"lastModified":"2025-09-02T07:24:07.000Z","likes":8,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false,"numParameters":508471808},{"author":"amphion","authorData":{"_id":"6562a925a72f05d2eaac5687","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","fullname":"Amphion","name":"amphion","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":408,"isUserFollowing":false},"downloads":5,"gated":false,"id":"amphion/TaDiCodec-TTS-AR-Qwen2.5-3B","availableInferenceProviders":[],"lastModified":"2025-08-26T21:55:57.000Z","likes":6,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false,"numParameters":3118942208},{"author":"amphion","authorData":{"_id":"6562a925a72f05d2eaac5687","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","fullname":"Amphion","name":"amphion","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":408,"isUserFollowing":false},"downloads":0,"gated":false,"id":"amphion/dualcodec-tts","availableInferenceProviders":[],"lastModified":"2025-06-03T05:04:57.000Z","likes":5,"private":false,"repoType":"model","isLikedByUser":false},{"author":"amphion","authorData":{"_id":"6562a925a72f05d2eaac5687","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","fullname":"Amphion","name":"amphion","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":408,"isUserFollowing":false},"downloads":14,"gated":false,"id":"amphion/Metis","availableInferenceProviders":[],"lastModified":"2025-04-13T10:47:41.000Z","likes":29,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false},{"author":"amphion","authorData":{"_id":"6562a925a72f05d2eaac5687","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","fullname":"Amphion","name":"amphion","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":408,"isUserFollowing":false},"downloads":14,"gated":false,"id":"amphion/Vevo","availableInferenceProviders":[],"lastModified":"2025-04-13T06:09:59.000Z","likes":45,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false}],"paperPreviews":[],"spaces":[{"author":"amphion","authorData":{"_id":"6562a925a72f05d2eaac5687","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","fullname":"Amphion","name":"amphion","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":408,"isUserFollowing":false},"colorFrom":"blue","colorTo":"purple","createdAt":"2025-09-19T11:28:32.000Z","emoji":"🚀","id":"amphion/AnyAccomp","lastModified":"2025-09-28T15:29:24.000Z","likes":7,"pinned":false,"private":false,"sdk":"gradio","repoType":"space","runtime":{"stage":"RUNNING","hardware":{"current":"zero-a10g","requested":"zero-a10g"},"storage":null,"gcTimeout":172800,"replicas":{"current":1,"requested":1},"devMode":false,"domains":[{"domain":"amphion-anyaccomp.hf.space","stage":"READY"}],"sha":"a59f096baf16f933c6ae5c7d79ecaeae4abff03d"},"shortDescription":"Generalizable Accompaniment Generation","title":"AnyAccomp","isLikedByUser":false,"ai_short_description":"Generate accompaniment for vocal or instrument audio","ai_category":"Music Generation","trendingScore":0,"tags":["gradio","region:us"],"featured":false},{"author":"amphion","authorData":{"_id":"6562a925a72f05d2eaac5687","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","fullname":"Amphion","name":"amphion","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":408,"isUserFollowing":false},"colorFrom":"pink","colorTo":"green","createdAt":"2024-07-16T09:14:49.000Z","emoji":"📈","id":"amphion/PicoAudio","lastModified":"2025-05-18T13:52:48.000Z","likes":28,"pinned":false,"private":false,"sdk":"gradio","repoType":"space","runtime":{"stage":"RUNTIME_ERROR","hardware":{"current":null,"requested":"zero-a10g"},"storage":null,"gcTimeout":172800,"errorMessage":"Exit code: ?. Reason: ","replicas":{"requested":1},"devMode":false,"domains":[{"domain":"amphion-picoaudio.hf.space","stage":"READY"}]},"title":"PicoAudio","isLikedByUser":false,"ai_short_description":"Generate audio from text descriptions with timestamps","ai_category":"Audio Generation","trendingScore":0,"tags":["gradio","region:us"],"featured":false},{"author":"amphion","authorData":{"_id":"6562a925a72f05d2eaac5687","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","fullname":"Amphion","name":"amphion","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":408,"isUserFollowing":false},"colorFrom":"indigo","colorTo":"yellow","createdAt":"2025-04-18T09:42:36.000Z","emoji":"🐠","id":"amphion/Vevo","lastModified":"2025-04-23T09:28:02.000Z","likes":100,"pinned":false,"private":false,"sdk":"gradio","repoType":"space","runtime":{"stage":"RUNTIME_ERROR","hardware":{"current":null,"requested":"zero-a10g"},"storage":null,"gcTimeout":172800,"errorMessage":"Launch timed out, workload was not healthy after 30 min","replicas":{"requested":1},"devMode":false,"domains":[{"domain":"amphion-vevo-demo.hf.space","stage":"READY"},{"domain":"amphion-vevo.hf.space","stage":"READY"}]},"shortDescription":"Controllable Zero-Shot Voice Imitation","title":"Vevo for Zero-shot VC, TTS, and More","isLikedByUser":false,"ai_short_description":"Transform audio style and timbre","ai_category":"Audio Transformation","trendingScore":0,"tags":["gradio","region:us"],"featured":true},{"author":"amphion","authorData":{"_id":"6562a925a72f05d2eaac5687","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","fullname":"Amphion","name":"amphion","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":408,"isUserFollowing":false},"colorFrom":"purple","colorTo":"purple","createdAt":"2024-10-18T11:42:08.000Z","emoji":"😻","id":"amphion/maskgct","lastModified":"2024-11-06T10:53:57.000Z","likes":260,"pinned":false,"private":false,"sdk":"gradio","repoType":"space","runtime":{"stage":"CONFIG_ERROR","hardware":{"current":null,"requested":"zero-a10g"},"storage":null,"gcTimeout":172800,"errorMessage":"No candidate PyTorch version found for ZeroGPU","replicas":{"requested":2},"domains":[{"domain":"amphion-maskgct.hf.space","stage":"READY"}]},"shortDescription":"MaskGCT TTS Demo","title":"MaskGCT TTS Demo","isLikedByUser":false,"ai_short_description":"Generate speech from text using a prompt audio","ai_category":"Speech Synthesis","trendingScore":0,"tags":["gradio","region:us"],"featured":false},{"author":"amphion","authorData":{"_id":"6562a925a72f05d2eaac5687","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","fullname":"Amphion","name":"amphion","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":408,"isUserFollowing":false},"colorFrom":"purple","colorTo":"indigo","createdAt":"2024-03-10T10:46:57.000Z","emoji":"🏃","id":"amphion/naturalspeech3_facodec","lastModified":"2024-10-18T12:06:47.000Z","likes":179,"pinned":false,"private":false,"sdk":"gradio","repoType":"space","runtime":{"stage":"CONFIG_ERROR","hardware":{"current":null,"requested":"zero-a10g"},"storage":null,"gcTimeout":172800,"errorMessage":"No candidate PyTorch version found for ZeroGPU","replicas":{"requested":1},"domains":[{"domain":"amphion-naturalspeech3-facodec.hf.space","stage":"READY"}]},"title":"NaturalSpeech3 FACodec","isLikedByUser":false,"ai_short_description":"Convert and reconstruct speech files","ai_category":"Voice Conversion","trendingScore":0,"tags":["gradio","region:us"],"featured":true}],"buckets":[],"numBuckets":0,"numDatasets":13,"numModels":26,"numSpaces":10,"lastOrgActivities":[{"time":"2026-02-02T15:34:11.889Z","user":"jiaqili3","userAvatarUrl":"/avatars/08651622fc1fd5089551b510be8c4530.svg","org":"amphion","orgAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60486b2cec955c4994bb6249/30H_QYVOsbkGBI83pYszQ.png","type":"discussion","discussionData":{"num":3,"author":{"_id":"642e68836a378e41aa54c3e9","avatarUrl":"/avatars/306139e1c1dd546cc8a9b5071f1ef5b3.svg","fullname":"Tim Scheffel","name":"TechInterMezzo","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false},"repo":{"name":"amphion/dualcodec","type":"model"},"title":"Dataset / License for weights?","status":"open","createdAt":"2026-02-02T14:54:14.000Z","isPullRequest":false,"numComments":3,"topReactions":[],"numReactionUsers":0,"pinned":false,"repoOwner":{"name":"amphion","isParticipating":true,"type":"org","isDiscussionAuthor":false}},"repoId":"amphion/dualcodec","repoType":"model","eventId":"6980c3f33afbbe91b146b4f9"},{"time":"2026-01-12T15:19:36.080Z","user":"yuantuo666","userAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/657fdd6b42fc53e18b89b856/kAPLFmH7Bq8WwE3hhDb9H.jpeg","type":"paper","paper":{"id":"2402.12660","title":"SingVisio: Visual Analytics of Diffusion Model for Singing Voice\n Conversion","publishedAt":"2024-02-20T02:16:24.000Z","upvotes":0,"isUpvotedByUser":false}},{"time":"2026-01-12T15:19:00.130Z","user":"yuantuo666","userAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/657fdd6b42fc53e18b89b856/kAPLFmH7Bq8WwE3hhDb9H.jpeg","type":"paper","paper":{"id":"2505.13000","title":"DualCodec: A Low-Frame-Rate, Semantically-Enhanced Neural Audio Codec\n for Speech Generation","publishedAt":"2025-05-19T11:41:08.000Z","upvotes":1,"isUpvotedByUser":true}}],"acceptLanguages":["*"],"canReadRepos":false,"canReadSpaces":false,"blogPosts":[],"currentRepoPage":0,"filters":{},"paperView":false}">Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
Amphion is An Open-Source Audio, Music, and Speech Generation Toolkit developed by a team led by Prof Zhizheng Wu from the Chinese University of Hong Kong, Shenzhen. The toolkit is developed in collaboration with OpenMMLab.
The North-Star objective of Amphion is to offer a platform for studying the conversion of any inputs into audio. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development. Amphion offers a unique feature: visualizations of classic models or architectures. We believe that these visualizations are beneficial for junior researchers and engineers who wish to gain a better understanding of the model.
Technical Report: https://huggingface.co/papers/2312.09911
Discord: https://discord.com/invite/ZxxREr3Y
Generalizable Accompaniment Generation
Generate audio from text descriptions with timestamps
Controllable Zero-Shot Voice Imitation
MaskGCT TTS Demo
Convert and reconstruct speech files