{
  "created_at": "2026-11-15T04:19:20Z",
  "files": [
    {
      "lfs": false,
      "path": ".gitattributes",
      "sha256": "df9c6c325bbb277e3548c45cb6aeabd20ad29a65eb1b33722943168343330095",
      "size": 5672
    },
    {
      "lfs": false,
      "path": "README.md",
      "sha256": "c7e50c840b04b4336b909cbe79af4d16badaf4b6adb6e63f6e9f351d9e69cddc",
      "size": 11865
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/README.md",
      "sha256": "b4cdef5ec9aa87429d9b988e8b6821a105032dc307cb6c256d77ce07fcabc3eb",
      "size": 27558
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/README_zh.md",
      "sha256": "6774dd4aadcfbb970e032f560093f12074548f10768d0c75bed466bb7d4bc01e",
      "size": 26569
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/app.py",
      "sha256": "c8c600129e36809315fdd77443f6db4dde4dbead9edada313e57c856363578f3",
      "size": 7043
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/assets/OpenMOSS_Logo.png",
      "sha256": "1693063e8714371ed4b04046d49173d120ce8c42d29168dd148afc555cb919d3",
      "size": 31912
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/assets/arc.png",
      "sha256": "54ae0abb8514ccc886823d5564a7584e73a417ae5e208f9679895d5b1a198a0e",
      "size": 978308
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/assets/arc2.png",
      "sha256": "326d3c4d14892046398892dd99352699597bb77d6dfbeef7eb120241a012e96b",
      "size": 5917051
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/assets/general_audio_bar.png",
      "sha256": "cfc72d328ab3670679a1532c56ae336227b7a595b21c0c6a06e06bf7f624fef1",
      "size": 176878
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/assets/general_audio_bar.svg",
      "sha256": "2c21f525e424456b868bae9b82f879383e889236f1dad7ca9ad222bc0d0dead8",
      "size": 90565
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/assets/mosi-logo.png",
      "sha256": "d83a75af3f1822ea51f8c5ee07df5de580d7edc734924a4ca706b1856878fcfe",
      "size": 25248
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/assets/moss-audio-architecture.svg",
      "sha256": "aedb0de1e38007b837044536a02ac16d101f1595741bee1d36207c723eadc146",
      "size": 1701262
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/assets/moss-audio-image.png",
      "sha256": "8277c7b1586c7adab911b493cd294d017f9f2e5ea7489556b0a5d16ca391f59a",
      "size": 2488568
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/assets/moss-audio-logo.png",
      "sha256": "1866d9a783acadea47aba654f2d82096aac2cf743ee41d0f236853ba35ca2c13",
      "size": 574060
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/assets/moss_audio_8b_thinking_metrics.svg",
      "sha256": "578b28d69bc15125bed137565bb70b33414179d4fac83bc95b02b44e6325b336",
      "size": 1701
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/assets/speech_caption_radar.png",
      "sha256": "ce19cfd19e3c6c681d1ce03d49c471e4eb644af997c73f471ba5ca81565066e6",
      "size": 479907
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/assets/speech_caption_radar.svg",
      "sha256": "eee76756f880336e82c459b44cdc3c682ab1f9b6c2393afc0880b668efe424a8",
      "size": 70582
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/assets/wechat.jpg",
      "sha256": "d14f8415797dbf747bf2236eb6a5f7d3ece7d5b6ba26f090b05f2e59e4a8b8bd",
      "size": 11066
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/assets/wechat.png",
      "sha256": "ac68172bb5b46a8da73a01cd3c48ff357d22f373b58c59316e3df8365fb9aefa",
      "size": 183388
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/audio/1c1c34433bac65da63c30b4d8b5fff177a134c2d32443dd7b4a808d1.wav",
      "sha256": "b520e4fc3752863bc839fd238b2d9222d4fee9f02ae139a542b857c3c805e132",
      "size": 4699628
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/demo/assets/audio/apple.mp3",
      "sha256": "3cb3b098bbb83b25632c14956e6598d580821e0158a22c39b46ae62618ce977b",
      "size": 49197
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/audio/faker_and_chovy.mp3",
      "sha256": "a471a0bb264223c78dd93024437481aa229fedf039ae4a6f00d81cf9c10d0579",
      "size": 237675
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/audio/game.mp3",
      "sha256": "1f9e29ab2d92efae90a37f0bbc76c33a7efe4b8b2047d55d0b7ec15ceb22b966",
      "size": 185089
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/audio/qilixiang.mp3",
      "sha256": "8edbe30894cb9e586ada254a26241a90deb507d0d9b94c8eca164d298d6db2ec",
      "size": 4877071
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/audio/test_en.mp3",
      "sha256": "1f9e29ab2d92efae90a37f0bbc76c33a7efe4b8b2047d55d0b7ec15ceb22b966",
      "size": 185089
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/audio/water.wav",
      "sha256": "b8d17eb429bf8e0b83ca23fbbbfbf9b7c6c199c45b530a9cd36581443cbc0e8c",
      "size": 5147084
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/audio/吴京1.m4a",
      "sha256": "16bfd680678bab515d0077bd207c5bbddae5f39e6ee10995fa30223317511465",
      "size": 538300
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/demo/assets/metadata.jsonl",
      "sha256": "d2da5d0c8cbbbba8a712dfe0e55688a3af98bb97bf4e953053c3c836300a7a9b",
      "size": 17718
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/picture/2apples.png",
      "sha256": "d643fe1d72ea87dbc842e55ff38e7a6f4abd516b7c190a73abef8ae25271e871",
      "size": 2254201
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/picture/arc.png",
      "sha256": "7533775b92f0fea6ddff36d740360c8aa8608f42b52126159b03f70b34f6f529",
      "size": 978916
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/demo/assets/picture/arc.svg",
      "sha256": "d5368bb2877768ac58fad9c6b90bbea85e8a8b4978031db8648045f6bd305db4",
      "size": 1698847
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/picture/donk.PNG",
      "sha256": "85af007e95b1d3b582aea72a6b81c39e4eb3bc4616946e20a348e4293dca426b",
      "size": 203767
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/picture/emergency.png",
      "sha256": "af43149ce5dd4700cbad52a3815145bea418aa3afc0b42a9a287bc23b8e1b207",
      "size": 1432294
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/picture/faker&chovy.PNG",
      "sha256": "8315e721f19d8c818120d6e51e75254f011ca688ad9be5f6fdd002824f67c1e1",
      "size": 1044788
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/picture/forest.png",
      "sha256": "b5bd7aa289a3ede8b104107b7ddac15e8045312bb8623e3c15b0521728b24950",
      "size": 2259906
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/picture/moss-audio-2.png",
      "sha256": "786ed71d165cc2e5fdb034d6f0ca38c00d52a4b481d6f0ba570b9881bfc41977",
      "size": 1359677
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/demo/assets/picture/moss-audio-8b-thinking-metrics.svg",
      "sha256": "578b28d69bc15125bed137565bb70b33414179d4fac83bc95b02b44e6325b336",
      "size": 1701
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/demo/assets/picture/moss-audio-architecture.svg",
      "sha256": "aedb0de1e38007b837044536a02ac16d101f1595741bee1d36207c723eadc146",
      "size": 1701262
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/picture/moss-audio-image.png",
      "sha256": "8277c7b1586c7adab911b493cd294d017f9f2e5ea7489556b0a5d16ca391f59a",
      "size": 2488568
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/picture/wujing.png",
      "sha256": "387ce22576e849aa2049f893f19af7904b0e1fded2128b2287aec5cd2fe42abd",
      "size": 380980
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/demo/assets/picture/七里香.png",
      "sha256": "4a7b7b01c848776e1096ae63f39b2b4a02d4aa7dd1e46b6996c935b6a1b17a78",
      "size": 1010013
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/demo/index.html",
      "sha256": "bec36054b0b4c5fd5b9dac2fc2b2d7f777cf5c34b57d4b39b1b3567c2457712f",
      "size": 26099
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/demo/package.json",
      "sha256": "b20f7e28e6e8758904a1cc5d16d344389b60883d8dd23eac1201d877aa78b61a",
      "size": 230
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/demo/script.js",
      "sha256": "fc48f3dc7d1b0d813c50e89337ebaa3477d1a191b531edf81aef7b4175b91830",
      "size": 28619
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/demo/styles.css",
      "sha256": "a54f6a141718ef86427a33ac345b68c00ce43b8b071c9c600e0d07f08eb432b3",
      "size": 24292
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/finetune/FINETUNE.md",
      "sha256": "59c90f30f0d591904e5bfae644c4ef7b41c5809d4138201c52f98113a2bf6a1e",
      "size": 4090
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/finetune/finetune.py",
      "sha256": "6dd3fb5cea4c4928913f8ef71bf98e49a65af2157209eefd4cec0f69210bca08",
      "size": 9896
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/infer.py",
      "sha256": "1d4014563deeab827949a0855240242eb65e375cf85e6dcdbc26ceab9a4ab5b7",
      "size": 1763
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/moss_audio_usage_guide.md",
      "sha256": "d7a3fa4cc03b40cc00f3c11ade9509fd8c615005e3ba98ce2bd051cefad4e0f7",
      "size": 20187
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/pyproject.toml",
      "sha256": "a936a262df3ee02a953922d3e9397e92d9619e0ad878bef91ea87039d1b13327",
      "size": 1188
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/src/__init__.py",
      "sha256": "b34dd106f333447fe38da1b432168e21be0a738dd66efcd253acdfd27bb95241",
      "size": 33
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/src/audio_io.py",
      "sha256": "7fcb817d7160b4382cb02f1857283a47b9a518e544a69d9f62932aa0b7e4f8ff",
      "size": 468
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/src/configuration_moss_audio.py",
      "sha256": "e597dca441ff7fb58a5ec43186fafdfce19f31dada4955b4910059baa5d52ebd",
      "size": 4670
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/src/hf_inference.py",
      "sha256": "73c70398ecfcd8bb7499462d88e12eb26c526bc1e77ae2c72ff956fbfb55e1dc",
      "size": 2988
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/src/modeling_moss_audio.py",
      "sha256": "a52513e518c68a0ba7c636a1ab0e12f7755ceebd0ae033235dc5e2551bfcbf9c",
      "size": 22932
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/src/processing_moss_audio.py",
      "sha256": "05fb788cbdc6482eded8d70f7d2f524bc0cdca47d001acab5661c11f02cc6fe6",
      "size": 14970
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/test/test_en.mp3",
      "sha256": "1f9e29ab2d92efae90a37f0bbc76c33a7efe4b8b2047d55d0b7ec15ceb22b966",
      "size": 185089
    },
    {
      "lfs": true,
      "path": "code/MOSS-Audio/test/test_kr.mp3",
      "sha256": "a471a0bb264223c78dd93024437481aa229fedf039ae4a6f00d81cf9c10d0579",
      "size": 237675
    },
    {
      "lfs": false,
      "path": "code/MOSS-Audio/test/test_zh.mp3",
      "sha256": "b3a3f167f8f5684616acd570a5303bb213ea5b9689a0477421aa9933ad5b3a08",
      "size": 86001
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/CONTRIBUTING.md",
      "sha256": "cba16108b4a4762ba1ef68533c50376ab43dabda9f2d34760ee7daea753bed8d",
      "size": 1816
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/Figures/DER.jpg",
      "sha256": "7472f1f44110da44ebfc49f7926096098c8598c0c63dd837cbace3748d9256d1",
      "size": 62653
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/Figures/MOS-preference.png",
      "sha256": "1bae2db570246512bbf162aa3fb9fd3b3c80d17c89f917fe133b5649d4fb1857",
      "size": 67221
    },
    {
      "lfs": true,
      "path": "code/VibeVoice/Figures/VibeVoice-TTS-results.jpg",
      "sha256": "5f78a62e936b7197ca78c1eb94fda8f3d4abaeb3fe6ee4dab3f4934fd0ba3c8c",
      "size": 133846
    },
    {
      "lfs": true,
      "path": "code/VibeVoice/Figures/VibeVoice.jpg",
      "sha256": "353803ce2be393700ff3dfedd0a522b88ebd294702d0d2f51b6f7b7fe65d344f",
      "size": 342394
    },
    {
      "lfs": true,
      "path": "code/VibeVoice/Figures/VibeVoice_ASR_archi.png",
      "sha256": "c5973094212c6c5c9c0bba6ee274e396ddbb272d8642f86c0d96c5b9e85dd52b",
      "size": 149474
    },
    {
      "lfs": true,
      "path": "code/VibeVoice/Figures/VibeVoice_Realtime.png",
      "sha256": "0386a7f577a66324c2b07cf3dff573bc805ce8687c8d6f8b5f3d6d04aed51250",
      "size": 123543
    },
    {
      "lfs": true,
      "path": "code/VibeVoice/Figures/VibeVoice_logo.png",
      "sha256": "c39206a2524b48f0413a54ac5e6d668d52ef22c4f5f1d57386d785ccb27a3f1d",
      "size": 1416808
    },
    {
      "lfs": true,
      "path": "code/VibeVoice/Figures/VibeVoice_logo_white.png",
      "sha256": "fc14f811c968062cf6a624b12043cf76b13c89597a240e78db08031c9e5a42ba",
      "size": 318208
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/Figures/cpWER.jpg",
      "sha256": "cd686c29637e4267ecb1119e68c973fe6782ef09e5b9fb136b5265b048255947",
      "size": 68492
    },
    {
      "lfs": true,
      "path": "code/VibeVoice/Figures/language_distribution_horizontal.png",
      "sha256": "1151d7587c660c7417df0194bbb7aeefe02a6be5a3ba8a89203d52a3602fa700",
      "size": 888409
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/Figures/tcpWER.jpg",
      "sha256": "1586b7b5635a9be4f1f67f8e31db639ca4382cc6dea747adff1afe37d27d0dc0",
      "size": 64251
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/LICENSE",
      "sha256": "98a96c38494df4963951e32b81ec4effebe4c8a812ab8d9e7d185d59e86fe2fc",
      "size": 1066
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/README.md",
      "sha256": "44d8870d2d1de1f23832776477afc559d9d01b8e4aff74f2558eea205f96f24b",
      "size": 10888
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/SECURITY.md",
      "sha256": "b02bf4e236e9335b27298a77688c751d18ca7e6052873d0d3d29eda37d0a72fa",
      "size": 542
    },
    {
      "lfs": true,
      "path": "code/VibeVoice/demo/asr_demo/demo1-chat.mp3",
      "sha256": "cfe9999ba960ca81bd0d23e288cd285459a345079deb4ff9dc668e8e43254dca",
      "size": 1104755
    },
    {
      "lfs": true,
      "path": "code/VibeVoice/demo/asr_demo/demo1-chat.mp4",
      "sha256": "c9ed73f3bf99de7ea67ae0c33886c7162244c2c93516a2eb7eb1ef11b64a53f8",
      "size": 6089204
    },
    {
      "lfs": true,
      "path": "code/VibeVoice/demo/asr_demo/demo2-song.mp3",
      "sha256": "042ab3f176179e5472e849d2d35e7c2964353c542ef75f25f821567beb301970",
      "size": 5741165
    },
    {
      "lfs": true,
      "path": "code/VibeVoice/demo/asr_demo/demo2-song.mp4",
      "sha256": "549e8a4e4f81c61526a0826948bcb070cb2e8ab0118bc95db12964218e5679fb",
      "size": 24233101
    },
    {
      "lfs": true,
      "path": "code/VibeVoice/demo/asr_demo/demo3-hotwords.wav",
      "sha256": "d4d31cd34f22b891e4fc88e666533a726bf77ee1f2ae2fe12f5880394572f4f2",
      "size": 1524138
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/demo/download_experimental_voices.sh",
      "sha256": "9436bd08bcd326e629313d559ed4c545120bff587f57600d55f0751c3f064618",
      "size": 2066
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/demo/realtime_model_inference_from_file.py",
      "sha256": "dc3b5cdae46682c69e873f26bd4b69a925a3bd6060c1be3ad3090413314131c5",
      "size": 12029
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/demo/text_examples/1p_abs.txt",
      "sha256": "7920dffbd957d6764e09530d1d0081538f71e23c569cfaacb4d26cb468b682c7",
      "size": 1068
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/demo/text_examples/1p_vibevoice.txt",
      "sha256": "36a8a0dc5a67d928537e34d5751d33145550cb58ce700378cc22b77e0139ed91",
      "size": 908
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/demo/vibevoice_asr_gradio_demo.py",
      "sha256": "e46112c49ee1e70a50e0203803fa7864674e6baf3ba1ba80faa92d033c1455ac",
      "size": 49351
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/demo/vibevoice_asr_inference_from_file.py",
      "sha256": "9337cb5ca1fc1d301a1c2fea0b5189a3e69d0b72184f823dce734da70ba55848",
      "size": 20608
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/demo/vibevoice_realtime_colab.ipynb",
      "sha256": "efcde517619dfdbc68a25098b47730fb53dc41a50b1c28a28d276bdd66a9ed87",
      "size": 6886
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/demo/vibevoice_realtime_demo.py",
      "sha256": "7b74622fa9e7bf424c8fdc4997183d5b4a1843fedacc198c8e903d015cc90a72",
      "size": 645
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/demo/web/app.py",
      "sha256": "66d6f2718c0fac1da5bd1ebd5b42843dc102edd3419c7bd1b8ed7b7ffb47df63",
      "size": 18047
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/demo/web/index.html",
      "sha256": "e313f1e7ca49c684910b71fd233f4b0192fa19905b06ece15a7f9be4a064f6c3",
      "size": 27379
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/docs/setup_gradio_demo.md",
      "sha256": "e0646579360375a1e5f5fe1997ba7a5620813fa00335c0826f9b22f042c495a7",
      "size": 5288
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/docs/vibevoice-asr.md",
      "sha256": "ed0d5f273a549461bec83696c899e249918e539965d9a525ce060914ba5662dc",
      "size": 5288
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/docs/vibevoice-realtime-0.5b.md",
      "sha256": "5bdb2d52a0677e32074fa03b25ddd4d758a8856499113e5dd7d42d13acd886fe",
      "size": 8095
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/docs/vibevoice-tts.md",
      "sha256": "0140eff932042c2afdc4aab11f32376b6961c9042a819dc1f50344ba8a33c7a5",
      "size": 8126
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/docs/vibevoice-vllm-asr.md",
      "sha256": "f0d83c662f4419f83350d76f9d3e4fe5365fa7ac5d64664baf41abd121ab7658",
      "size": 6317
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/finetuning-asr/README.md",
      "sha256": "0dde0faf3f195f31f8b4807cf76d8356a1b9a3d2e12fc2e69e8e173901a34b5d",
      "size": 4184
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/finetuning-asr/inference_lora.py",
      "sha256": "25325ef95f3ae9d0b1d5962e8b4024c72624352723e1372b10eba68390eda510",
      "size": 6422
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/finetuning-asr/lora_finetune.py",
      "sha256": "5e6b91b496747b135ab1018bdcac6f944da0e71caedcdfe3b713a1ab93b6bbe8",
      "size": 18750
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/finetuning-asr/toy_dataset/0.json",
      "sha256": "3c11af2c56e3150a5942782bbafe7dfe29fd3686d35d200e807ce2e15140ee34",
      "size": 8462
    },
    {
      "lfs": true,
      "path": "code/VibeVoice/finetuning-asr/toy_dataset/0.mp3",
      "sha256": "f0be61c3de38f627b9c965f98c8a884eb7d13b0a1e136a595b8664e08eb6de12",
      "size": 3191877
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/finetuning-asr/toy_dataset/1.json",
      "sha256": "75a6cdbc5711ee461e559a58529a91c9b7e238219a45e82e051d1433c26402c0",
      "size": 6500
    },
    {
      "lfs": true,
      "path": "code/VibeVoice/finetuning-asr/toy_dataset/1.mp3",
      "sha256": "128e42ad687c15efacf56c400d605e32afd4d08545c80c16b7a36191275aadec",
      "size": 2604597
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/pyproject.toml",
      "sha256": "6887842e9e9c417541684b73b8db4d0c44fc9a7ce4cf0f49f333da1f376cd6f2",
      "size": 1195
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice.egg-info/PKG-INFO",
      "sha256": "0312bbec76a1db0f2d15cd7b301ae42e0dd76fe9030da4888d6167f11f6d9986",
      "size": 11941
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice.egg-info/SOURCES.txt",
      "sha256": "3abb2d39bc22d4653b95087b1f9fa318bb0128317b8a74e75b79463794882e0d",
      "size": 1432
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice.egg-info/dependency_links.txt",
      "sha256": "01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b",
      "size": 1
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice.egg-info/entry_points.txt",
      "sha256": "2d0f3827331e614ec067602921497c76768e6ea9a5a30e38ce7aa3526f39d566",
      "size": 66
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice.egg-info/requires.txt",
      "sha256": "1f1eaa9dd579558dcb906e39c27332a179e91f12a380e9f4fe9a4e07f70312a9",
      "size": 229
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice.egg-info/top_level.txt",
      "sha256": "ab7ef64da72393b1b2218f116354d9e77c4f91c75c76ec6335e1e0475079ced8",
      "size": 22
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/__init__.py",
      "sha256": "d2545b8b4f70348514a367a04ae38d0da3de98174a88745cdb5e64bb0e4b6839",
      "size": 422
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/configs/qwen2.5_1.5b_64k.json",
      "sha256": "6d65b90d0703453ce9aa27de2cbca87e0cc276f82acfc0d388538400e429238c",
      "size": 2692
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/configs/qwen2.5_7b_32k.json",
      "sha256": "a890a296f0c62bc8d62ead244fdd6a3738d2a67dc6c0634fe9aa3f8064047c5e",
      "size": 2730
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/modular/__init__.py",
      "sha256": "a5453c864eedead47a9d52a03d78e8893bb9983dc3e93ca9ef1205e6803d7448",
      "size": 589
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/modular/configuration_vibevoice.py",
      "sha256": "bcf59d8749405d5d25436923444436f6719cb9b2b403941a8a5e46f5b94873d0",
      "size": 16434
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/modular/configuration_vibevoice_streaming.py",
      "sha256": "1b4417ea2ffe5b42a58d1ee6b3c9508bc253930c2d55f8ec1f10916e36b8029e",
      "size": 4667
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/modular/modeling_vibevoice.py",
      "sha256": "6a7fbe0f967f09cd05c2cbbd270276bac8e90a6061510a82029cbf8bc680caf2",
      "size": 22454
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/modular/modeling_vibevoice_asr.py",
      "sha256": "b6408126af0a478c8ccb28bb71ce0212bbb3a262d040de76dcd02c09db54d042",
      "size": 23012
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/modular/modeling_vibevoice_streaming.py",
      "sha256": "96d402716fe2cc6284c4ad7f8b2309dd8d06d2133681e266387466116e908afb",
      "size": 8031
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/modular/modeling_vibevoice_streaming_inference.py",
      "sha256": "cb5360a62dbf3a836cea763348bc6330c4d7a422fbe572f4abf7b3c7a15bce8b",
      "size": 42627
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/modular/modular_vibevoice_diffusion_head.py",
      "sha256": "8a90ac685b9e32793749e2c58b48906758486d8b0bc0d92c8dfd141aa053852e",
      "size": 9222
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/modular/modular_vibevoice_text_tokenizer.py",
      "sha256": "9f188a3b1d21fbeb8eb26b62693a8ffa1024edff29af28c5d8599c9ade143f7f",
      "size": 10895
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/modular/modular_vibevoice_tokenizer.py",
      "sha256": "f2fdcdaff26a685510c982634cad3be8258b299f89566a87188c932fd85f816d",
      "size": 51899
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/modular/streamer.py",
      "sha256": "e6129f46e2c61466ca96ce479c04adfaad32f483230f4d3531c96717bd16f603",
      "size": 9492
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/processor/__init__.py",
      "sha256": "957a1c1b18310691647cc0adaece1d8f940785deaa4d8d17ece2059bee0b9dc8",
      "size": 378
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/processor/audio_utils.py",
      "sha256": "e15f184c18f754862e38082836b9c19c0f97c03c939412ab856838dc30788bcf",
      "size": 6478
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/processor/vibevoice_asr_processor.py",
      "sha256": "e5551319fac744b5152202a8e41888dad2d94d3fa941aa755d0888caa5a6a4ab",
      "size": 23414
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/processor/vibevoice_processor.py",
      "sha256": "5b28fa5247a83cb65385e06428fb112369f50723e343d7b38c7a6e7e1dfddab5",
      "size": 30082
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/processor/vibevoice_streaming_processor.py",
      "sha256": "41ff57a7da668db9099c395ab7bbee9b2cd7aa0c2f8f0b0c214768c051aa5a53",
      "size": 18620
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/processor/vibevoice_tokenizer_processor.py",
      "sha256": "3b18571d3b5cac91211412f03c3a8477bb0242173a4a53a633498cac470f1068",
      "size": 15682
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/schedule/__init__.py",
      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
      "size": 0
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/schedule/dpm_solver.py",
      "sha256": "be10eae978afda40a6bc082806fa1e8f0f4b4e451fd1d21cec97347116ffba73",
      "size": 49964
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/schedule/timestep_sampler.py",
      "sha256": "70b003bdfdc716d09942ecfcd0e2f438bac27ea16da9527e105e008a0069dd83",
      "size": 701
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vibevoice/scripts/__init__.py",
      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
      "size": 0
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vllm_plugin/__init__.py",
      "sha256": "e18602c23e18d277bdeeab3fb161c8772bb38ff3cb5732b5944b644c2d7c4630",
      "size": 2503
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vllm_plugin/inputs.py",
      "sha256": "e7bfc6faa1a69533f847533f293c5d9075385bdf087f17966e220baa619229e1",
      "size": 3723
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vllm_plugin/model.py",
      "sha256": "32573cee608486e08ba58fc6a72f653c221dace21d58254cc321c9863c48752a",
      "size": 52432
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vllm_plugin/scripts/gradio_asr_demo_api_video.py",
      "sha256": "206ddfcb49eeae5b0d8de162b5749258e7048fa61e99d22ef81cb76794488dbe",
      "size": 88246
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vllm_plugin/scripts/start_server.py",
      "sha256": "7627359f0f3d438483965cfaba4d64d540bba45672f52cd238979d35cabc1cfb",
      "size": 14946
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vllm_plugin/tests/test_api.py",
      "sha256": "2de94bf0f3dcbe68d17c7f2d1c3370df5c5e3cbe882d037d08d09cb4b9033a34",
      "size": 8846
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vllm_plugin/tests/test_api_auto_recover.py",
      "sha256": "ca9b66ae612b184b42f02751d59a980e2d664cf1d8cc2d8661961b28d1bb442d",
      "size": 24687
    },
    {
      "lfs": false,
      "path": "code/VibeVoice/vllm_plugin/tools/generate_tokenizer_files.py",
      "sha256": "e68728a18370b3284e090b6fe410214328f947d237240e2e2395de2fff1e68ec",
      "size": 20906
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/README.md",
      "sha256": "98edd84e9c7f3f8d09a9f12ccc68555aeae7f21a1b45aa1bf0ec710dc9358a1f",
      "size": 20784
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/README.md",
      "sha256": "23a74dd4616eb6ecc78e07f68d021facc8becfef2fb409b5c9f2f4bd0787d0eb",
      "size": 4735
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/build_report.py",
      "sha256": "3484cbf07c9a609f05d625ef783b19acc69fe25b6b9e547866a5632370ff08eb",
      "size": 8949
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/prepare_audio.py",
      "sha256": "4d45d8679c97f9a19b9739d94039d131b22c2e10cf59d1112787ec948974067e",
      "size": 1984
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/run_all.sh",
      "sha256": "83678cdd712383569ae940c470825a7e251654a40b2139f3f99328cb5fdcab24",
      "size": 4663
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/setup_environments.sh",
      "sha256": "806f3b16256b9967f516438637172079f436d138ee65394f9cd322cbdfd270f4",
      "size": 4433
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/workers/_common.py",
      "sha256": "308ac222018890f000f59cfbd51fd4d368b9969fdab0413ffd4df0ddc9b4a575",
      "size": 3447
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/workers/stage1_nemotron_sortformer.py",
      "sha256": "26c913708cdb3e3a2930d58fa2459ed72a1286dcc7d9a45bd9c7a6a8f9f969d8",
      "size": 1592
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/workers/stage1a_vibevoice.py",
      "sha256": "7e9d6de5c67f289be1949469305a573a09082783f32581f13ccf934f88fc36f1",
      "size": 1175
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/workers/stage1b_parakeet.py",
      "sha256": "0b6760406baf9728f398eac28a401fe88921a941aff4192e8fe0fcc7fc2280ca",
      "size": 1317
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/workers/stage1c_qwen3.py",
      "sha256": "0b862a253573db695c1c47bb84e9e475b7cf036ebeedc898823080baa6bf3f7d",
      "size": 1044
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/workers/stage2_whisper_experts.py",
      "sha256": "8399ce42ec07570428a8615db8868e1ec520d320aff3f8aebf39812950340615",
      "size": 1359
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/workers/stage3_sfx_lora.py",
      "sha256": "b657fadf57be5b17fda9c70dbdfbf7b6bf91c1427f9476347bc4c326048a3e0b",
      "size": 1429
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/workers/stage3b_vocalburst.py",
      "sha256": "9a2af5df68493171292015f1b72bc0c9c1e09b9f94cd162f9260984e1a983eac",
      "size": 2552
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/workers/stage4_moss_annotator.py",
      "sha256": "7110cbfbfda3822ddb0c405d3418db03584b2b71e005b0c6ac4f5d23761b6ef2",
      "size": 3325
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/workers/stage5_gemma_fusion.py",
      "sha256": "f522dbc871f53ec1000ffcd36278549c47ca9ab9a5df601ea654e63d2fd5c17f",
      "size": 1942
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/workers/stage_dicow.py",
      "sha256": "d45d02cdf18eb24425c862f38d03ba0e53a9e62608fb15ce78f5cb2aed07b493",
      "size": 1142
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/default_pipeline/workers/stage_pyannote_diar.py",
      "sha256": "def91da29b39b5280ac89dbb3aa73d2e7867397defd98a1de9bb5d693680ae03",
      "size": 1330
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/docs/default_pipeline.md",
      "sha256": "6ecbb00457ea5fe9df5e6adc873f5135767d902a953e0b920cd054b44eb5770e",
      "size": 8409
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/docs/evaluation_results.md",
      "sha256": "715bae2cb5d596baf28af50a28091e9e8a610d849501e584b9863559982e1549",
      "size": 5393
    },
    {
      "lfs": true,
      "path": "code/universal-audio-annotation-pipeline/docs/gemma12_dicow_demo.html",
      "sha256": "3720bb42ca36f959c36adf591ef84c34e1c64b32012dd5a33b623b7b99604ea8",
      "size": 14338221
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/docs/pipeline_details.md",
      "sha256": "f1c647913641c4534f0c13d352934c1f13620ed4747bba58ad3e8a980f912fa2",
      "size": 6608
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/docs/predictions/frankenstein.html",
      "sha256": "0aabc449933abdf2c77053f98749bd90593e35caa6728da1cc93f17d964c1a98",
      "size": 3092671
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/docs/predictions/index.html",
      "sha256": "bb651c86d9df01cf1448193381f821e03851bbaeb463d1b3f3feefa5ce714fb2",
      "size": 9035411
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/docs/soundscape_comparison.html",
      "sha256": "b093d74120be64874f6c06c3c508b86995b8db7ca841051f1006053f61efc7ae",
      "size": 16076
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/docs/training_lora.md",
      "sha256": "c1140625e28b4bc8862b75c3cd6a0da78db77493f329e8471465c2b96bc6cbf6",
      "size": 3197
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/evaluation/build_html_report.py",
      "sha256": "85e79e2af615309a32a55b59732299b515667e019c670c7e80e0d9cbbd82e6f8",
      "size": 45355
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/evaluation/eval_triple_asr.py",
      "sha256": "f3a3968f82821a84fa1b8d16b70bda618f7320d541676b444035153587bc65ea",
      "size": 32316
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/evaluation/gemini_judge.py",
      "sha256": "d4ba43c7a2bd979f5393217de6a0f99fa0ae0aedf62abe0cbb8643b849a7f0cc",
      "size": 7721
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/examples/sample_output.json",
      "sha256": "7a5eeddb682d6e1c37dff3a2d7959c9f6c1fb36c3055fbbaee1a5c0b7ee0fc24",
      "size": 1008
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/examples/sample_predictions/synth_00_pred.json",
      "sha256": "7a5eeddb682d6e1c37dff3a2d7959c9f6c1fb36c3055fbbaee1a5c0b7ee0fc24",
      "size": 1008
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/examples/sample_predictions/synth_10_pred.json",
      "sha256": "f718f47e71366f3e71d9ed1403c82f8a99a902e7d5899f24e6422868dd7df1c8",
      "size": 1833
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/examples/sample_predictions/synth_25_pred.json",
      "sha256": "60ddb8fc452bed4ac23e50234dfd0546e8184bfbbb7cf9263521f5faecd0dcf7",
      "size": 1794
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/examples/sample_predictions/yt_00_pred.json",
      "sha256": "2093ad0ad408e0408936073435c37e74cceca2dcd9c4b107d4ec1a7ee978e4f1",
      "size": 5112
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/examples/sample_predictions/yt_05_pred.json",
      "sha256": "fc98780d406686c475e535b36141daa5db23a53613af0142ead16cb0cb964677",
      "size": 1643
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/pipeline/__init__.py",
      "sha256": "8b10375fc05d248f7abc68e837437e2305e70ec7d36bb9e2fc41e13571f8f219",
      "size": 225
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/pipeline/asr_dicow.py",
      "sha256": "2d440aa012e5b3d849296ee7452b9992ca9be059657edffa601fc022b122436a",
      "size": 4103
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/pipeline/asr_nemotron.py",
      "sha256": "6b8701cf9bd6f5b979760f198e5ec99324856cbb617d91673a78255da54e507d",
      "size": 5621
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/pipeline/asr_parakeet.py",
      "sha256": "4dbad87a707fe49d7fbdb226301edd5a68f280228871fb235c9a033d0277acfe",
      "size": 5661
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/pipeline/asr_qwen3.py",
      "sha256": "7c3c80cc621cce370939d0cc33545e7964a44c179ea8e32b7636b565d73968eb",
      "size": 4352
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/pipeline/asr_vibevoice.py",
      "sha256": "98410dc30ede5d6ec4e06767cdc0a1bbaf3ffd2ee27d987cd3e92711680947fd",
      "size": 4572
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/pipeline/diarize_pyannote.py",
      "sha256": "f649b2ac56734f6d0dbe643e693809f2ec684088de042da6d5eb6d579e5f7087",
      "size": 2137
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/pipeline/gemma_fusion.py",
      "sha256": "b12d45ca63dc6a51d545f84435bd3d1948efb037828fea49ddeac1995ee290a1",
      "size": 6023
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/pipeline/moss_annotator.py",
      "sha256": "6098864ab52734824ada3c9d5facb4cce35fde97b9b8fb35f9ac4d44d71f23d6",
      "size": 35508
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/pipeline/run_pipeline.py",
      "sha256": "2328dc4bc85422bb7099e76187286b64651096455ff7b6c48b07732f3bf80af3",
      "size": 8205
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/pipeline/sfx_lora.py",
      "sha256": "0590c0eb8305ebb904eb16102e44591b53a33c59056adc9b933391e7f13bb7bf",
      "size": 5430
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/pipeline/utils.py",
      "sha256": "d54f794cb8fed55623d1d1aba42cef076052ead3396f9544bff06eed9d46f65f",
      "size": 9806
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/pipeline/vocalburst_locator.py",
      "sha256": "491373cd2726d1b102ba21cf0dd3dcc4dacf6a08bb62f72d627d55bbeb83630c",
      "size": 9981
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/pipeline/whisper_experts.py",
      "sha256": "55598c1a0a0c6f79bb77341d1dae6af7c0521b0a8b3651c2c435a8e2d11cd683",
      "size": 3951
    },
    {
      "lfs": false,
      "path": "code/universal-audio-annotation-pipeline/requirements.txt",
      "sha256": "f015fed78013e53f917517c63cfc7d1fe0a7cf80ba2aef83929be5c698472e75",
      "size": 179
    },
    {
      "lfs": false,
      "path": "models/bud-e-whisper/added_tokens.json",
      "sha256": "9715fd2243b6f06a5858b5e32950d2853f73dd5bc201aafcf76f5082a2d8acd1",
      "size": 34604
    },
    {
      "lfs": false,
      "path": "models/bud-e-whisper/config.json",
      "sha256": "199b4ed36c036908f3b54b5bef47a04fd721587e2ed2c8e33a80369ace168a8f",
      "size": 1427
    },
    {
      "lfs": false,
      "path": "models/bud-e-whisper/generation_config.json",
      "sha256": "445fa0dc13ccd9da93f91285f80eb92b1ab1ef7376a034a15a4c43f36ff62ec3",
      "size": 3841
    },
    {
      "lfs": false,
      "path": "models/bud-e-whisper/merges.txt",
      "sha256": "2df2990a395e35e8dfbc7511e08c12d56018d8d04691e0133e5d63b21e154dc6",
      "size": 493869
    },
    {
      "lfs": true,
      "path": "models/bud-e-whisper/model.safetensors",
      "sha256": "7bbd466bf003d717fcc17119bc2619165dba237aaf2b47bc727e494539c1351d",
      "size": 966995080
    },
    {
      "lfs": false,
      "path": "models/bud-e-whisper/normalizer.json",
      "sha256": "bf1c507dc8724ca9cf9903640dacfb69dae2f00edee4f21ceba106a7392f26dd",
      "size": 52666
    },
    {
      "lfs": false,
      "path": "models/bud-e-whisper/preprocessor_config.json",
      "sha256": "a6a76d28c93edb273669eb9e0b0636a2bddbb1272c3261e47b7ca6dfdbac1b8d",
      "size": 339
    },
    {
      "lfs": false,
      "path": "models/bud-e-whisper/special_tokens_map.json",
      "sha256": "e67ae3a0aaa99abcd9f187138e12db1f65c16a14761c50ef10eef2c174a7a691",
      "size": 2194
    },
    {
      "lfs": false,
      "path": "models/bud-e-whisper/tokenizer_config.json",
      "sha256": "21a4fc0483c14b87f4e0bbc177a9a357479bfa7c95aaf21ad53d71e9c5afafb9",
      "size": 282713
    },
    {
      "lfs": false,
      "path": "models/bud-e-whisper/vocab.json",
      "sha256": "50d6a919f0a0601d56a04eb583c780d18553aa388254ba3158eb6a00f13e2c1a",
      "size": 1036584
    },
    {
      "lfs": true,
      "path": "models/diar_sortformer_4spk-v1/diar_sortformer_4spk-v1.nemo",
      "sha256": "bc74dfd8ca314240abcdc7e2949901eeaa72947a04ce1fab893e373d81f1e689",
      "size": 493434880
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/.gitattributes",
      "sha256": "f1346224cbc78dc6c53bad682468ba1c0e82daf15a32b9e600326e26718c1429",
      "size": 1570
    },
    {
      "lfs": true,
      "path": "models/dicow-v3_3/DiCoW_v3_3.png",
      "sha256": "511159b854facd36c733ddcb6a1c79f465cac80c3ab5d381a182c4e5d7c42449",
      "size": 123315
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/FDDT.py",
      "sha256": "fe8b1dec493fdae366b5474de3d1ac0004adcac80036533dacd1ea5f35e0c945",
      "size": 3996
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/README.md",
      "sha256": "89273d11872afea90761526312bb3cf35d71ca2f05bc73bd34a8c789276a4e21",
      "size": 5545
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/added_tokens.json",
      "sha256": "3c51f66c4c21f9e126970078f11ae77a78c74aee8df606ee9daba86e467108e0",
      "size": 34648
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/config.json",
      "sha256": "8a7767c79feab0d8277f11b85825fc6258fcf7cf5b104e6cddd954de5c3e456b",
      "size": 2000
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/config.py",
      "sha256": "fc9eea09841fb6558e68dda42c327332005b5145b144d2fddfe463bff3e9c971",
      "size": 2558
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/decoding.py",
      "sha256": "b713399e01804690b84eea5e4cd58d5c475d8da4217835478a364bff15243f46",
      "size": 16250
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/encoder.py",
      "sha256": "ec63648d28e0950ed4e4b0651bf651c60aab613a3bc603b6a9a97f704dc325ef",
      "size": 10887
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/generation.py",
      "sha256": "a91f671083f385f9dd4469e1f2c24e85fe2ddbd089c572905e5f8259a6cdd38a",
      "size": 58224
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/generation_config.json",
      "sha256": "5f16cf3f2d75b6b24946f6855455af784574c8a6098326742653ce4ea7648b47",
      "size": 3733
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/layers.py",
      "sha256": "e91a8af1e4d62e5b112032e42b89796b3430a0c05c49f8c5031dff6e37c8a842",
      "size": 8518
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/merges.txt",
      "sha256": "2df2990a395e35e8dfbc7511e08c12d56018d8d04691e0133e5d63b21e154dc6",
      "size": 493869
    },
    {
      "lfs": true,
      "path": "models/dicow-v3_3/model.safetensors",
      "sha256": "73dee45746bb4a6e5e99d8553f582a70b21b6f1499dea68433d6a7178eb4183b",
      "size": 3568074944
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/modeling_dicow.py",
      "sha256": "aa335c71078cfad5b84b5e323dd56f232289552a0052b02693819a591e1049b1",
      "size": 15126
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/normalizer.json",
      "sha256": "bf1c507dc8724ca9cf9903640dacfb69dae2f00edee4f21ceba106a7392f26dd",
      "size": 52666
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/preprocessor_config.json",
      "sha256": "654cf18d3e163b948ceaf9766da56ce0b52de265d58673cf61c9376f126bd499",
      "size": 357
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/special_tokens_map.json",
      "sha256": "baea4ea09372eb4fca86b4e4346139fd73cb807d5087e9de0948e971739c3e74",
      "size": 2186
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/tokenizer.json",
      "sha256": "5c1bf30c9e716e1477bedef846b01be0013daecb89e9e3ef7ab89b23c178df1b",
      "size": 3930645
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/tokenizer_config.json",
      "sha256": "3c75940dfce3a294fca7041a5faff011677f1b68fa85e47511bb8cf6dccaded6",
      "size": 282873
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/utils.py",
      "sha256": "f25f0617517f7ed604361643dc875fc5d2d3500376134dbbe240c82688b6714b",
      "size": 540
    },
    {
      "lfs": false,
      "path": "models/dicow-v3_3/vocab.json",
      "sha256": "6788c80b082e9b0d1393147d3a3e62ba19285ac0c82ace8e5ef00f37ead58971",
      "size": 835528
    },
    {
      "lfs": true,
      "path": "models/gemma-4-12b-it-gguf/gemma-4-12b-it-Q8_0.gguf",
      "sha256": "74d2d4f0b5b08ca8589d1a5f50e689c0984469f3cedbdc7d67458c6e9e35496a",
      "size": 12669646240
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-instruct/added_tokens.json",
      "sha256": "1fabcc983ee0051b922009b1b5a7af1844385f38783e62679ac35d6dd2aa3355",
      "size": 801
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-instruct/chat_template.jinja",
      "sha256": "87a2728cb8dc9fe424d624542f6060ec05a1d285ebbec578bb078900e33396b5",
      "size": 4116
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-instruct/config.json",
      "sha256": "535154c2a5bcbd0e18e2f92bcf370ac74b530eec97ad4fd9317993ba0a316536",
      "size": 2715
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-instruct/generation_config.json",
      "sha256": "bb52bfdd308deaea4ec800bf0165e75770b0a4e5c105963bee1b0398f4043d3e",
      "size": 121
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-instruct/merges.txt",
      "sha256": "8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5",
      "size": 1671853
    },
    {
      "lfs": true,
      "path": "models/moss-audio-8b-instruct/model-00001-of-00004.safetensors",
      "sha256": "ead244c31d39119e1447f31ff04d7a52698c8352553fec472c6284ed6828c3d6",
      "size": 4931218512
    },
    {
      "lfs": true,
      "path": "models/moss-audio-8b-instruct/model-00002-of-00004.safetensors",
      "sha256": "cdfb0c2c3c1c98208cd40bb72bbeda4faa2436dca55fc461b535e6e9a80736d6",
      "size": 4983069720
    },
    {
      "lfs": true,
      "path": "models/moss-audio-8b-instruct/model-00003-of-00004.safetensors",
      "sha256": "eeaeb7cb4575954150f43f81c83988abe48a45d668aed637ce5bf4f0d0d050b8",
      "size": 4999847608
    },
    {
      "lfs": true,
      "path": "models/moss-audio-8b-instruct/model-00004-of-00004.safetensors",
      "sha256": "2e9a71c1548f6850c6113e94a3ecafde650a1b4e870c3bca5b686ed744c68792",
      "size": 3190899536
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-instruct/model.safetensors.index.json",
      "sha256": "d980986e77df7ff3b427ffdff58b0ca04e9a93d2e4a097ed2187cef6593a8e67",
      "size": 80030
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-instruct/special_tokens_map.json",
      "sha256": "76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd",
      "size": 613
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-instruct/tokenizer_config.json",
      "sha256": "0869e41f5d123ff144a811f0d83c5d18871dcd4b4064f46bf9def194bfbc6f41",
      "size": 6114
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-instruct/vocab.json",
      "sha256": "87a257b04b17642a0688c98cd1df89c398bda4fee532d6f88b38a659ecb4ac8d",
      "size": 3383407
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-thinking/added_tokens.json",
      "sha256": "1fabcc983ee0051b922009b1b5a7af1844385f38783e62679ac35d6dd2aa3355",
      "size": 801
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-thinking/chat_template.jinja",
      "sha256": "87a2728cb8dc9fe424d624542f6060ec05a1d285ebbec578bb078900e33396b5",
      "size": 4116
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-thinking/config.json",
      "sha256": "535154c2a5bcbd0e18e2f92bcf370ac74b530eec97ad4fd9317993ba0a316536",
      "size": 2715
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-thinking/generation_config.json",
      "sha256": "bb52bfdd308deaea4ec800bf0165e75770b0a4e5c105963bee1b0398f4043d3e",
      "size": 121
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-thinking/merges.txt",
      "sha256": "8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5",
      "size": 1671853
    },
    {
      "lfs": true,
      "path": "models/moss-audio-8b-thinking/model-00001-of-00004.safetensors",
      "sha256": "5444e22367fe81bc56f5fff3693e6e788984452325cf90f645724d7f85fe2ee6",
      "size": 4931218512
    },
    {
      "lfs": true,
      "path": "models/moss-audio-8b-thinking/model-00002-of-00004.safetensors",
      "sha256": "c6dd174db4db22bc72a4e7aeb99bb6a3de5d8af6c53036a1ce215c621eb8252b",
      "size": 4983069720
    },
    {
      "lfs": true,
      "path": "models/moss-audio-8b-thinking/model-00003-of-00004.safetensors",
      "sha256": "a49edfcecb911b9b65c5f57b0596a935e867a56358587c39b612705cf90ec5b7",
      "size": 4999847608
    },
    {
      "lfs": true,
      "path": "models/moss-audio-8b-thinking/model-00004-of-00004.safetensors",
      "sha256": "9078bd9267da1452ece38bc7ea4400a34b69a9a3fa6f467e79390acc096855ba",
      "size": 3190899536
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-thinking/model.safetensors.index.json",
      "sha256": "d980986e77df7ff3b427ffdff58b0ca04e9a93d2e4a097ed2187cef6593a8e67",
      "size": 80030
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-thinking/special_tokens_map.json",
      "sha256": "76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd",
      "size": 613
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-thinking/tokenizer_config.json",
      "sha256": "0869e41f5d123ff144a811f0d83c5d18871dcd4b4064f46bf9def194bfbc6f41",
      "size": 6114
    },
    {
      "lfs": false,
      "path": "models/moss-audio-8b-thinking/vocab.json",
      "sha256": "87a257b04b17642a0688c98cd1df89c398bda4fee532d6f88b38a659ecb4ac8d",
      "size": 3383407
    },
    {
      "lfs": false,
      "path": "models/moss-audio-sfx-lora-v4/.gitattributes",
      "sha256": "11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361",
      "size": 1519
    },
    {
      "lfs": false,
      "path": "models/moss-audio-sfx-lora-v4/README.md",
      "sha256": "9caee3a070ae790fc61912a5c6114d9517c08570abfebe00f57dca22b227c580",
      "size": 6448
    },
    {
      "lfs": false,
      "path": "models/moss-audio-sfx-lora-v4/adapter_config.json",
      "sha256": "08857e37e5b9ef72aac500e1f197497757b2b64de28998b29903008398081313",
      "size": 1069
    },
    {
      "lfs": true,
      "path": "models/moss-audio-sfx-lora-v4/adapter_model.safetensors",
      "sha256": "394bdb06d1713c4319807f6cc334e7e76ce363d6dcd0ac32fc9ade347bd0b01f",
      "size": 698425272
    },
    {
      "lfs": false,
      "path": "models/moss-audio-sfx-lora-v4/inference.py",
      "sha256": "d9f38b2ca4ebeb9e14b70f4c1b2b765a53fccbed976ff00589beaf853e4eb924",
      "size": 6011
    },
    {
      "lfs": false,
      "path": "models/moss-audio-sfx-lora-v4/train.py",
      "sha256": "b1bfbb9876cdeabf1abef0a3bf35f36ae426a0648db3f34d02ae831fafb44204",
      "size": 15711
    },
    {
      "lfs": false,
      "path": "models/moss-audio-sfx-lora-v4/trainer_state.json",
      "sha256": "61a2ad5fce3f11a91c849ea28cdfe0d08dc6f5eb1d257dede1c6d58d921164fd",
      "size": 48793
    },
    {
      "lfs": true,
      "path": "models/moss-audio-sfx-lora-v4/training_args.bin",
      "sha256": "04bb7fb923759bf39d49b883193c9f65b8bd3a56c0102d9777ae549349c22a5b",
      "size": 7096
    },
    {
      "lfs": false,
      "path": "models/nemotron-3.5-asr-streaming-0.6b/.gitattributes",
      "sha256": "41df4a45d17e816c51b935c8f58de9d59f14276bec49d19f80a73e12c9437ee7",
      "size": 1604
    },
    {
      "lfs": false,
      "path": "models/nemotron-3.5-asr-streaming-0.6b/README.md",
      "sha256": "7d03f6f3c9b52463964cb68950d89da3446c0b17a81586ec44cb059d275751e2",
      "size": 47395
    },
    {
      "lfs": false,
      "path": "models/nemotron-3.5-asr-streaming-0.6b/arch_slide10.png",
      "sha256": "2be5d8ccfcd8232c6fc57ffacda125221382ef181ec239e1b6fdd78cf0c1c020",
      "size": 87843
    },
    {
      "lfs": false,
      "path": "models/nemotron-3.5-asr-streaming-0.6b/avg_wer_summary.png",
      "sha256": "9a5474f81b64e0ce844c5907f073f7fab56a353d21db9196cd11aba22f787060",
      "size": 65515
    },
    {
      "lfs": false,
      "path": "models/nemotron-3.5-asr-streaming-0.6b/bias.md",
      "sha256": "c867da097b69770c3c12d06debbb7df9d8fbf63764fb8a8bad0fee01a98e61c2",
      "size": 2104
    },
    {
      "lfs": false,
      "path": "models/nemotron-3.5-asr-streaming-0.6b/explainability.md",
      "sha256": "0f7b9ef8481da911bc54d2f57ba0960cad80f74a6acbc7e4fd5dd57d1fc2d93a",
      "size": 2388
    },
    {
      "lfs": false,
      "path": "models/nemotron-3.5-asr-streaming-0.6b/fleurs_langid_vs_auto.png",
      "sha256": "56c360a710c99cbf70c04006ec1f842b3796b72f5093178d438b2140049b3626",
      "size": 83849
    },
    {
      "lfs": false,
      "path": "models/nemotron-3.5-asr-streaming-0.6b/fleurs_wer_vs_chunk_size.png",
      "sha256": "9b340101e45a7ba6268f1b9c90037d9c2cf00c2c1768272bd3bdcaffd9b231ff",
      "size": 92234
    },
    {
      "lfs": true,
      "path": "models/nemotron-3.5-asr-streaming-0.6b/latency_vs_parallel.png",
      "sha256": "3e5636204786c68914f69c3f3158b4e698774b6e0dbd9120dbd996947e396638",
      "size": 139167
    },
    {
      "lfs": true,
      "path": "models/nemotron-3.5-asr-streaming-0.6b/model_architecture.png",
      "sha256": "3146643d1a7c8dd424adcb221a5dabbda6951da1ef3937f7d15b29e46e5fa272",
      "size": 150586
    },
    {
      "lfs": true,
      "path": "models/nemotron-3.5-asr-streaming-0.6b/model_overview.png",
      "sha256": "e4fa275d1d6cb0b01064df92c051dc0888dc63d18a8b3c8ae9b35268f2c89427",
      "size": 205324
    },
    {
      "lfs": true,
      "path": "models/nemotron-3.5-asr-streaming-0.6b/nemotron-3.5-asr-streaming-0.6b.nemo",
      "sha256": "210214ed94039bf6bfbb9a047c7fa289628db75b103e2bf6381fa78285436a74",
      "size": 2368284501
    },
    {
      "lfs": false,
      "path": "models/nemotron-3.5-asr-streaming-0.6b/privacy.md",
      "sha256": "c662e372f07b12892e4a6f6d5d74abb503b82931fa74c3ef959859719ef5788b",
      "size": 2097
    },
    {
      "lfs": false,
      "path": "models/nemotron-3.5-asr-streaming-0.6b/safety.md",
      "sha256": "0eb7a4d7eac77d0a3a1af275a73d69b94989dcc04ddb905f06937ac36d6dd3c2",
      "size": 737
    },
    {
      "lfs": false,
      "path": "models/nemotron-3.5-asr-streaming-0.6b/throughput_vs_chunk.png",
      "sha256": "276b2f4e3dca6f5550f4215c8180ab244bc998401d65b54ce40400d228fee5da",
      "size": 69454
    },
    {
      "lfs": true,
      "path": "models/parakeet-tdt-0.6b-v3/parakeet-tdt-0.6b-v3.nemo",
      "sha256": "3cbdc85877e668ca7b82d0d56770eb1fac76691f55d6b97545e8d61ca588d10d",
      "size": 2509332480
    },
    {
      "lfs": false,
      "path": "models/pyannote-segmentation-3.0/.gitattributes",
      "sha256": "11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361",
      "size": 1519
    },
    {
      "lfs": false,
      "path": "models/pyannote-segmentation-3.0/LICENSE",
      "sha256": "63a777ad4b3c7aed4b260b084d8fb49ec781c46c70c6b599ca5d2402ef7ebe50",
      "size": 1061
    },
    {
      "lfs": false,
      "path": "models/pyannote-segmentation-3.0/README.md",
      "sha256": "a37bc19811cc1a52a4c128c33207813b1558b4e49b050b03e814d0a96d14f05d",
      "size": 4648
    },
    {
      "lfs": false,
      "path": "models/pyannote-segmentation-3.0/config.yaml",
      "sha256": "fa65a47a751602f04cc570135007d76859b69e8f9f1bfdf5878a5145980d4263",
      "size": 399
    },
    {
      "lfs": false,
      "path": "models/pyannote-segmentation-3.0/example.png",
      "sha256": "996ead1eebae55de59f0c9e5d1cbb8ecec5f995db8bdfda2d9cb39fa473fb409",
      "size": 69284
    },
    {
      "lfs": true,
      "path": "models/pyannote-segmentation-3.0/pytorch_model.bin",
      "sha256": "da85c29829d4002daedd676e012936488234d9255e65e86dfab9bec6b1729298",
      "size": 5905440
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/.gitattributes",
      "sha256": "11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361",
      "size": 1519
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/.github/workflows/sync_to_hub.yaml",
      "sha256": "eb3bc63c9ea65f3e80aff8d9d21add1cad1b501adb99658374225c07d1eea225",
      "size": 467
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/README.md",
      "sha256": "8af30a33044bf34a51bbef3d87695c204894d172e9aae6f018417ce0066f0cb5",
      "size": 10985
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/config.yaml",
      "sha256": "04ad9cd59a93c3a7c754200ecc9e1c4ba87bf1657ef8a4debf7555e711daeeda",
      "size": 469
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/handler.py",
      "sha256": "2ca97765f7449ca4113d20d437326a289cc56d10621528309323ae6d95375697",
      "size": 2167
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/AISHELL.SpeakerDiarization.Benchmark.test.eval",
      "sha256": "fad3376adff04c9e640e9113dc1dcb6fead0356e48dc085f4a119b8e36dd4c74",
      "size": 3359
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/AISHELL.SpeakerDiarization.Benchmark.test.rttm",
      "sha256": "854117735efbe2e241644d3f7043eeb394f2cf129d80010d275dee3207d1f7f4",
      "size": 624408
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/AMI-SDM.SpeakerDiarization.Benchmark.test.eval",
      "sha256": "5ee47e65376643a32c9435c4b9e207a66db0502ed63932af9c07c0db894ade4f",
      "size": 2699
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/AMI-SDM.SpeakerDiarization.Benchmark.test.rttm",
      "sha256": "88dcf21e6b0469eeefd8b6fb87a563977fd3d98f5c56715c64a64fd579451233",
      "size": 572959
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/AMI.SpeakerDiarization.Benchmark.test.eval",
      "sha256": "ac46e261261e77918e3c05e64705822eb4513b78f7a1fec372d8ed5c3c6efd02",
      "size": 2699
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/AMI.SpeakerDiarization.Benchmark.test.rttm",
      "sha256": "11a7c7e8913fd20f9bb8f74411474f1c88b56490bdd422cf9564d8830c9e3050",
      "size": 572817
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/AVA-AVD.SpeakerDiarization.Benchmark.test.eval",
      "sha256": "9794ae8de21c106b0167b2968c951c9d2ef1b1c049fa69d2ca22b54822211fed",
      "size": 8235
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/AVA-AVD.SpeakerDiarization.Benchmark.test.rttm",
      "sha256": "2875422d81307d4d0fb5d5eaae75c10e46d7653fbbd1b50a197bc8b92172ace5",
      "size": 365238
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/AliMeeting.SpeakerDiarization.Benchmark.test.eval",
      "sha256": "2864f0d5675eea6b161775171e89db755b76cc3f3991d091c4e8b0e19c40ba65",
      "size": 3479
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/AliMeeting.SpeakerDiarization.Benchmark.test.rttm",
      "sha256": "1db7ddfa6813ff583e257963a6a129ed915a8926b4196545c435767812739b95",
      "size": 940136
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/DIHARD.SpeakerDiarization.Benchmark.test.eval",
      "sha256": "a5a2094f3bbc07301bc3540e0067122734c99d80d75ae385a71f29b4828d7faa",
      "size": 37082
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/DIHARD.SpeakerDiarization.Benchmark.test.rttm",
      "sha256": "2b84e395bbe9cae3a52493cd43969fb38c8ea9ac456824ddeffec8c309219bc9",
      "size": 3600418
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/MSDWILD.SpeakerDiarization.Benchmark.test.eval",
      "sha256": "4a7f9b3897ecb24b79ab9c14f4401c5bcb81dd9396a8b6d0cbcf3c75927ac2eb",
      "size": 65701
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/MSDWILD.SpeakerDiarization.Benchmark.test.rttm",
      "sha256": "aad5a0d52cc5acdf33dcc15e059d9676552073c23df9faaf6bdb8acc315bf191",
      "size": 648416
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/REPERE.SpeakerDiarization.Benchmark.test.eval",
      "sha256": "16b0ecef05e28cb39b85e4fd0e02e8eff122ec2f8db43bbe197a698a7c13089b",
      "size": 10724
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/REPERE.SpeakerDiarization.Benchmark.test.rttm",
      "sha256": "fa7d7453750b9d6ca043a8f84b4a5c53dd727e4f9f5b517e58ac0f550a60d33c",
      "size": 1441591
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/VoxConverse.SpeakerDiarization.Benchmark.test.eval",
      "sha256": "799039fcf58c6c3cb242b9a3cd2716b8e66f2dbdcc63ceb988c766819d421c55",
      "size": 31859
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/reproducible_research/VoxConverse.SpeakerDiarization.Benchmark.test.rttm",
      "sha256": "49b52da0238719c18606ffa5e369c0ffbf18c01e2fd12942cc4c70da337c15ff",
      "size": 1979557
    },
    {
      "lfs": false,
      "path": "models/pyannote-speaker-diarization-3.1/requirements.txt",
      "sha256": "bb450fa73fc3f0156f9affea74e66900e42c23c81b9d9da70d30312e28fdf149",
      "size": 21
    },
    {
      "lfs": false,
      "path": "models/pyannote-wespeaker-voxceleb-resnet34-LM/.gitattributes",
      "sha256": "11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361",
      "size": 1519
    },
    {
      "lfs": false,
      "path": "models/pyannote-wespeaker-voxceleb-resnet34-LM/README.md",
      "sha256": "ffc47d6f225a9341771a8304c0b8a354f706184956737661cb2c695e310551e3",
      "size": 3319
    },
    {
      "lfs": false,
      "path": "models/pyannote-wespeaker-voxceleb-resnet34-LM/config.yaml",
      "sha256": "6ff718cff3c5d7a4493537ab7f4780cad7e3d32453f59099b4076aefa07a9974",
      "size": 221
    },
    {
      "lfs": true,
      "path": "models/pyannote-wespeaker-voxceleb-resnet34-LM/pytorch_model.bin",
      "sha256": "366edf44f4c80889a3eb7a9d7bdf02c4aede3127f7dd15e274dcdb826b143c56",
      "size": 26645418
    },
    {
      "lfs": false,
      "path": "models/qwen3-asr-1.7b/chat_template.json",
      "sha256": "75a8cfca24f00de72d796fbfed6858fc9614ef3dabd8696684cc3bc03a9c58ff",
      "size": 1161
    },
    {
      "lfs": false,
      "path": "models/qwen3-asr-1.7b/config.json",
      "sha256": "2e74a751548b8ad7d7526d29365ad8144c345d8b412b1152d25dc6698452712f",
      "size": 6194
    },
    {
      "lfs": false,
      "path": "models/qwen3-asr-1.7b/generation_config.json",
      "sha256": "1da527824d81e07118facff437e03f2e24a23311e3bdeb2368973fe77e5f275c",
      "size": 142
    },
    {
      "lfs": false,
      "path": "models/qwen3-asr-1.7b/merges.txt",
      "sha256": "8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5",
      "size": 1671853
    },
    {
      "lfs": true,
      "path": "models/qwen3-asr-1.7b/model-00001-of-00002.safetensors",
      "sha256": "a4cd1f1a04d90b757dc7f7dd26254e69a013b19e80efe590a83c6a3bde8608d6",
      "size": 4220320824
    },
    {
      "lfs": true,
      "path": "models/qwen3-asr-1.7b/model-00002-of-00002.safetensors",
      "sha256": "6e0b9d9e09e2e0238e7ef3cc8a484ab387e91b90f1900bedf88bc92d7929ccfc",
      "size": 478200688
    },
    {
      "lfs": false,
      "path": "models/qwen3-asr-1.7b/model.safetensors.index.json",
      "sha256": "f994739fe38e5210b9e3e8ce6c6307315e2ceac3cb630e7b7414d69dce520f60",
      "size": 64821
    },
    {
      "lfs": false,
      "path": "models/qwen3-asr-1.7b/preprocessor_config.json",
      "sha256": "45e120a4eda2c20c5d7f2ea9354e63536bf35e27aa573fb7cdf78017b378770d",
      "size": 330
    },
    {
      "lfs": false,
      "path": "models/qwen3-asr-1.7b/tokenizer_config.json",
      "sha256": "4942d005604266809309cabc9f4e9cb89ce855d59b14681fdc0e1cc62ea26c4c",
      "size": 12487
    },
    {
      "lfs": false,
      "path": "models/qwen3-asr-1.7b/vocab.json",
      "sha256": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910",
      "size": 2776833
    },
    {
      "lfs": false,
      "path": "models/qwen3-forcedaligner-0.6b/chat_template.json",
      "sha256": "75a8cfca24f00de72d796fbfed6858fc9614ef3dabd8696684cc3bc03a9c58ff",
      "size": 1161
    },
    {
      "lfs": false,
      "path": "models/qwen3-forcedaligner-0.6b/config.json",
      "sha256": "d616c65d46c4b90bdc651b0a0963ea932732241140f337f9bb6b0335a9c8ef09",
      "size": 5982
    },
    {
      "lfs": false,
      "path": "models/qwen3-forcedaligner-0.6b/generation_config.json",
      "sha256": "948d089b23bca1d214e768d59c4438365665f52ec6d33678f4062206b3fbbb8c",
      "size": 115
    },
    {
      "lfs": false,
      "path": "models/qwen3-forcedaligner-0.6b/merges.txt",
      "sha256": "8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5",
      "size": 1671853
    },
    {
      "lfs": true,
      "path": "models/qwen3-forcedaligner-0.6b/model.safetensors",
      "sha256": "47831d0e82f96b20e9034dba01a075ee06436654719f6a68289e49f1b65ce0e7",
      "size": 1835544544
    },
    {
      "lfs": false,
      "path": "models/qwen3-forcedaligner-0.6b/preprocessor_config.json",
      "sha256": "45e120a4eda2c20c5d7f2ea9354e63536bf35e27aa573fb7cdf78017b378770d",
      "size": 330
    },
    {
      "lfs": false,
      "path": "models/qwen3-forcedaligner-0.6b/tokenizer_config.json",
      "sha256": "3ab80063f8511deb9566e6ad438d17b7a6277fcffd52d92854112f19d36bd81c",
      "size": 12666
    },
    {
      "lfs": false,
      "path": "models/qwen3-forcedaligner-0.6b/vocab.json",
      "sha256": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910",
      "size": 2776833
    },
    {
      "lfs": false,
      "path": "models/sound-effect-captioning-whisper/config.json",
      "sha256": "6559865e39b729a063a8ac0a8407d8af67d8cc9367652fc4496f88364d554c6d",
      "size": 1302
    },
    {
      "lfs": false,
      "path": "models/sound-effect-captioning-whisper/generation_config.json",
      "sha256": "10f7e09cafc14b9d92a41c3b10abd9e3370fbc71ff6ae469bfe9c725e076ebb0",
      "size": 3773
    },
    {
      "lfs": true,
      "path": "models/sound-effect-captioning-whisper/model.safetensors",
      "sha256": "9e15eab5eda6c51c8bc6fb60208a0b4ab3e74b25cdf200a4ccb773b093921da5",
      "size": 966995080
    },
    {
      "lfs": false,
      "path": "models/sound-effect-captioning-whisper/preprocessor_config.json",
      "sha256": "ba2e601484abc80f4cded977f9a4fd4a53175b7d35c2f2511f0cfc3a32ad2499",
      "size": 315
    },
    {
      "lfs": false,
      "path": "models/sound-effect-captioning-whisper/processor_config.json",
      "sha256": "8c648fa85aafc59a07435ed751322499bd4238b819ca9200ddd2b5ba4df50e68",
      "size": 409
    },
    {
      "lfs": false,
      "path": "models/sound-effect-captioning-whisper/tokenizer.json",
      "sha256": "7b469ff15eb7816315aa45eec391f5943d639b9d73d110f5c003df5192fd54e3",
      "size": 3930494
    },
    {
      "lfs": false,
      "path": "models/sound-effect-captioning-whisper/tokenizer_config.json",
      "sha256": "61af73c493c67b2a426c9f998fcd214592ffd12e0fdd53950122d28e5777ac4a",
      "size": 2083
    },
    {
      "lfs": false,
      "path": "models/timbre-whisper/config.json",
      "sha256": "71c6a4996318496e1aa5f41136c7226c981296d9478e1ba370e7fd676c676835",
      "size": 1230
    },
    {
      "lfs": false,
      "path": "models/timbre-whisper/generation_config.json",
      "sha256": "515f6b58bfe4b9ac69425ce8491c49762de8e8d217f10cf4b055bc2b596da429",
      "size": 2908
    },
    {
      "lfs": true,
      "path": "models/timbre-whisper/model.safetensors",
      "sha256": "7633d10378c0bb3b260e96e9e13a40b9997ee1f0d06e8f03230317c8ab551590",
      "size": 966995080
    },
    {
      "lfs": false,
      "path": "models/vibevoice-asr/config.json",
      "sha256": "1798906d016a625ffa0100182cad152e055bfee53fb228a45ffe25d8179b9b24",
      "size": 3520
    },
    {
      "lfs": true,
      "path": "models/vibevoice-asr/model-00001-of-00008.safetensors",
      "sha256": "5548c67885d423ba184bc8c33f2e9f81b582a6d119cef79907e19a274b916637",
      "size": 2488346272
    },
    {
      "lfs": true,
      "path": "models/vibevoice-asr/model-00002-of-00008.safetensors",
      "sha256": "163023c61a3fb047745cbaf53ed41c1e27e515e9786a376e122bfac2ea6e687e",
      "size": 2389315976
    },
    {
      "lfs": true,
      "path": "models/vibevoice-asr/model-00003-of-00008.safetensors",
      "sha256": "4e021702dfac2c52e8fdd6688de82c118be7bb7ad9b5c7988725ec63c44a64fb",
      "size": 2466376368
    },
    {
      "lfs": true,
      "path": "models/vibevoice-asr/model-00004-of-00008.safetensors",
      "sha256": "b17657bb151daa117a5a4671374ac1b248acb696691a2a67ac227a1115925e30",
      "size": 2466376400
    },
    {
      "lfs": true,
      "path": "models/vibevoice-asr/model-00005-of-00008.safetensors",
      "sha256": "0ed4e457268f7b02dda5cffe16b3a32614ccc2ccfe5de2db39bdd79700836406",
      "size": 2499431136
    },
    {
      "lfs": true,
      "path": "models/vibevoice-asr/model-00006-of-00008.safetensors",
      "sha256": "6de8246bb042fd853b57d40995efd289ea44e4d1b611cec2e122570b8d2122bd",
      "size": 2483469928
    },
    {
      "lfs": true,
      "path": "models/vibevoice-asr/model-00007-of-00008.safetensors",
      "sha256": "a2ba6960d994dc7598efc6796f85ab097da7708f4dd56095f7fccf4df8dc00e5",
      "size": 1464887482
    },
    {
      "lfs": true,
      "path": "models/vibevoice-asr/model-00008-of-00008.safetensors",
      "sha256": "1b9d9b328f85a25b4efca712d31513c6eed9e178152cc8cf4a6f0c2cd2bb623f",
      "size": 1089994848
    },
    {
      "lfs": false,
      "path": "models/vibevoice-asr/model.safetensors.index.json",
      "sha256": "1468c7b7c74fe27831d8db57871fbf15efd270c747f3f99caf689119ace658ba",
      "size": 120151
    },
    {
      "lfs": true,
      "path": "models/vocalburst-locator/model.pt",
      "sha256": "28feecb8b76154e6fed5f7b044ff7245f0f97505caceec9606083ca10633cd8f",
      "size": 972377238
    },
    {
      "lfs": false,
      "path": "models/voice-tagging-whisper/config.json",
      "sha256": "d9be29f6f5c78f6d16044ac2bd72eebdb8768927e4bc9afa00903918c44665af",
      "size": 1332
    },
    {
      "lfs": false,
      "path": "models/voice-tagging-whisper/generation_config.json",
      "sha256": "050ac3e58301c4c2cba4be7d0f9f2b77c5e1ca77d96540832a025f071fcdd973",
      "size": 3744
    },
    {
      "lfs": true,
      "path": "models/voice-tagging-whisper/model.safetensors",
      "sha256": "345a605f146b3ded57edc0a8ca4134c7f3e328437061dc4d16fc546af9216d8f",
      "size": 966995080
    },
    {
      "lfs": false,
      "path": "models/whisper-small/added_tokens.json",
      "sha256": "9715fd2243b6f06a5858b5e32950d2853f73dd5bc201aafcf76f5082a2d8acd1",
      "size": 34604
    },
    {
      "lfs": false,
      "path": "models/whisper-small/config.json",
      "sha256": "e6a2b489da1b5aed65a8eb8d1e7466fa867ad5643a8bc138ba708bd56b2875c4",
      "size": 1967
    },
    {
      "lfs": false,
      "path": "models/whisper-small/merges.txt",
      "sha256": "2df2990a395e35e8dfbc7511e08c12d56018d8d04691e0133e5d63b21e154dc6",
      "size": 493869
    },
    {
      "lfs": true,
      "path": "models/whisper-small/model.safetensors",
      "sha256": "1d7734884874f1a1513ed9aa760a4f8e97aaa02fd6d93a3a85d27b2ae9ca596b",
      "size": 966995080
    },
    {
      "lfs": false,
      "path": "models/whisper-small/normalizer.json",
      "sha256": "bf1c507dc8724ca9cf9903640dacfb69dae2f00edee4f21ceba106a7392f26dd",
      "size": 52666
    },
    {
      "lfs": false,
      "path": "models/whisper-small/preprocessor_config.json",
      "sha256": "9b5cd03a36fbb8a627c64d98a5b5b126ead95a77720723944487311f0110b666",
      "size": 184990
    },
    {
      "lfs": false,
      "path": "models/whisper-small/special_tokens_map.json",
      "sha256": "e67ae3a0aaa99abcd9f187138e12db1f65c16a14761c50ef10eef2c174a7a691",
      "size": 2194
    },
    {
      "lfs": false,
      "path": "models/whisper-small/tokenizer.json",
      "sha256": "27fc476bfe7f17299480be2273fc0608e4d5a99aba2ab5dec5374b4482d1a566",
      "size": 2480466
    },
    {
      "lfs": false,
      "path": "models/whisper-small/tokenizer_config.json",
      "sha256": "2a4c4281cf9f51ac6ccc406fdc711a087afe6530f671fa7b80953edc498275ce",
      "size": 282683
    },
    {
      "lfs": false,
      "path": "models/whisper-small/vocab.json",
      "sha256": "8f680bba319e01a653d2e8a5dbc17a9157179e0576e6ce74ce0c06356c6e24f9",
      "size": 835550
    },
    {
      "lfs": false,
      "path": "predictions/frankenstein.html",
      "sha256": "0aabc449933abdf2c77053f98749bd90593e35caa6728da1cc93f17d964c1a98",
      "size": 3092671
    },
    {
      "lfs": false,
      "path": "predictions/index.html",
      "sha256": "bb651c86d9df01cf1448193381f821e03851bbaeb463d1b3f3feefa5ce714fb2",
      "size": 9035411
    }
  ],
  "generator": "freeweights-manifest/0.1.0",
  "id": "laion/universal-audio-annotation-pipeline",
  "license": {
    "file_path": "README.md",
    "file_sha256": "c7e50c840b04b4336b909cbe79af4d16badaf4b6adb6e63f6e9f351d9e69cddc",
    "id": "Apache-2.0",
    "name": "Apache License 2.0",
    "redistribution": "yes"
  },
  "schema_version": 0,
  "section": "alt.freeweights.text",
  "sources": [
    {
      "last_checked": "2026-11-15T04:19:20Z",
      "priority": 100,
      "type": "source",
      "url": "https://huggingface.co/laion/universal-audio-annotation-pipeline/resolve/fa563e8fd6e8c584e33256d9b0b47775143cb60b/"
    }
  ],
  "upstream": {
    "commit": "fa563e8fd6e8c584e33256d9b0b47775143cb60b",
    "host": "huggingface.co",
    "repo": "laion/universal-audio-annotation-pipeline",
    "url": "https://huggingface.co/laion/universal-audio-annotation-pipeline/tree/fa563e8fd6e8c584e33256d9b0b47775143cb60b"
  }
}
