tolkio-models / models.json
datacrunch's picture
Spoken language classifier (Silero, MIT) with the Asian and African packs
9e65491 verified
Raw History Blame Contribute Delete
12.1 kB
{
"version": 1,
"baseUrl": "https://huggingface.co/datacrunch/tolkio-models/resolve/main/",
"packs": [
{
"id": "core",
"name": "Speech, translation and voice",
"about": "Needed to translate",
"required": true,
"default": true,
"files": [
{
"path": "asr/encoder.onnx",
"size": 190174181,
"sha256": "0485d0d91292af10054e922847d3638f25a85ec8fbe363321420069b6df96f4e"
},
{
"path": "asr/decoder.onnx",
"size": 12257616,
"sha256": "20be91b65239bf94e3d823b7976b3116b1eb81acfac4968b8ca74647bfb3c2a4"
},
{
"path": "asr/joiner.onnx",
"size": 5940845,
"sha256": "5b7bb09b75586fde2205db90b4e93a5c6c4e4dfd0acc8c49ea03d190eb78874c"
},
{
"path": "asr/tokens.txt",
"size": 93939,
"sha256": "d58544679ea4bc6ac563d1f545eb7d474bd6cfa467f0a6e2c1dc1c7d37e3c35d"
},
{
"path": "vad/silero_vad.onnx",
"size": 643854,
"sha256": "9e2449e1087496d8d4caba907f23e0bd3f78d91fa552479bb9c23ac09cbb1fd6"
},
{
"path": "mt/model.gguf",
"size": 1236740608,
"sha256": "f490c26c4378dfab8d730b9d60060544a3ec2ba5120af3e859a3b8195dde09e8"
},
{
"path": "mt/translator.json",
"size": 90,
"sha256": "75cea1e83f56854fb09bbdc5963c7f88e72bc914ae5abfd92a79e991c03cdb4a"
},
{
"path": "tts/duration_predictor.int8.onnx",
"size": 3700147,
"sha256": "c3eb91414d5ff8a7a239b7fe9e34e7e2bf8a8140d8375ffb14718b1c639325db"
},
{
"path": "tts/text_encoder.int8.onnx",
"size": 36416150,
"sha256": "c7befd5ea8c3119769e8a6c1486c4edc6a3bc8365c67621c881bbb774b9902ff"
},
{
"path": "tts/vector_estimator.onnx",
"size": 256534781,
"sha256": "883ac868ea0275ef0e991524dc64f16b3c0376efd7c320af6b53f5b780d7c61c"
},
{
"path": "tts/vocoder.onnx",
"size": 50810860,
"sha256": "69f157736d9599c47145f7fe19a461083a9d9fe7462e898f8665957e0259a942"
},
{
"path": "tts/tts.json",
"size": 8253,
"sha256": "42078d3aef1cd43ab43021f3c54f47d2d75ceb4e75f627f118890128b06a0d09"
},
{
"path": "tts/unicode_indexer.bin",
"size": 262144,
"sha256": "8402ca48e5189a8950138580b0fff64db6f072f24ac07cd54ba8b2fbb9883b30"
},
{
"path": "tts/voice.bin",
"size": 517168,
"sha256": "67d5209b0ee8ce6c74105ffbe12fe6a7628aea3b4ba2fcb308a4a67938a93ce8"
},
{
"path": "tts/vector_estimator.int8.onnx",
"size": 78400833,
"sha256": "20cd86fa5c6effedfda0e7cffe5b0569ca401c440a0c3a1d72bf39286c0db3fd"
},
{
"path": "tts/vocoder.int8.onnx",
"size": 25991073,
"sha256": "e923d60f53f95eb1ce235f1dc33ec56d9c057823c96fa6f8acf98f32b0da6152"
}
]
},
{
"id": "mt13",
"name": "Best-quality translator",
"about": "8-bit translation model: slightly better wording, a little slower, needs 8 GB of memory",
"required": false,
"default": false,
"files": [
{
"path": "mt13/model.gguf",
"size": 2076674560,
"sha256": "a09d287f41d297206947a2e51acc29dd03c8b22356111fdb1e289c0c97c173f3"
},
{
"path": "mt13/translator.json",
"size": 97,
"sha256": "f88440b373ee840efbea4948c5af1026fd63eabf2be6cb133a5f1971ac543f16"
}
]
},
{
"id": "spk",
"name": "Tell speakers apart",
"about": "Recognizes each person by voice and separates people talking at once",
"required": false,
"default": false,
"files": [
{
"path": "spk/speaker.onnx",
"size": 14778545,
"sha256": "4cc1e52dd69c2e0c6e5ddef5c5718956c9ac91e22d0bc13303dd29c7ea758733"
},
{
"path": "spk/segmentation.onnx",
"size": 1540506,
"sha256": "d582f4b4c6b48205de7e0643c57df0df5615a3c176189be3fc461e9d18827b5d"
},
{
"path": "spk/separator.onnx",
"size": 23086538,
"sha256": "404df1d29ab90955d1d7dce9efffbe2f1b63567ae4da2e2e146acb65cb97ea7c"
}
]
},
{
"id": "africa",
"name": "African languages",
"about": "Hears, translates and speaks 19 African languages (Swahili, Hausa, Yoruba, Zulu, Amharic and more), English to and from each, with 10 voices",
"required": false,
"default": false,
"files": [
{
"path": "africa/asr/model.int8.onnx",
"size": 365841453,
"sha256": "e3042b2f3b3ef0af2211bf99d2b4bf94a21f5ac0e9898827e7dd6d003a860e91"
},
{
"path": "africa/asr/tokens.txt",
"size": 90630,
"sha256": "7d99997ef207ff14c2cfe825f2aa037528ea250113cc3c6392bfe49326884ba6"
},
{
"path": "africa/mt/model.gguf",
"size": 644485184,
"sha256": "b4900f806d527bbae52e8d5a3f11f68fc72c27edd3238d22d5aefd2478a8dd59"
},
{
"path": "africa/mt/translator.json",
"size": 86,
"sha256": "c448b92f55fecc9f3b814b71db1f76f683d6628edd23ca972fa2964d746f8375"
},
{
"path": "voices/sw/voice.onnx",
"size": 57770413,
"sha256": "56c702d8cfdf0fe1fb6c8717b8331eeb57d7c7f2d66cee8eb95244d9ed336fa8"
},
{
"path": "voices/sw/voice.json",
"size": 674,
"sha256": "fb4ba729529a9d44f4850dd3bca6b1b002e257a17ccf7433129ad4daa3498521"
},
{
"path": "voices/ha/voice.onnx",
"size": 57779247,
"sha256": "3efcf0b33a01ec78feb2765b3a25760e010bd238430099c288f10ba7f0739ba0"
},
{
"path": "voices/ha/voice.json",
"size": 879,
"sha256": "d7668980977d5c159d77d1156df5fd916654e14bab0d8e1c21e965b14a51ee04"
},
{
"path": "voices/yo/voice.onnx",
"size": 57775407,
"sha256": "964bdd737b349edd09d32e9b327a5388a968f259c2b0cb8439473912d04b5325"
},
{
"path": "voices/yo/voice.json",
"size": 795,
"sha256": "91272f7d58189279d46c3909d6be34d65c65dd131fe5b9b4366981e8967d15df"
},
{
"path": "voices/ig/voice.onnx",
"size": 57782319,
"sha256": "e653a8e1f9683bd6f5b530be00f300cab98d282ad99c4bef786b2039aefa545e"
},
{
"path": "voices/ig/voice.json",
"size": 951,
"sha256": "3d7a8420c93d4c8f922804e3fa65efdea52070ed918acd7bbee6e1d09e80e08b"
},
{
"path": "voices/ln/voice.onnx",
"size": 57770029,
"sha256": "eb4f0b6c83a355e45035f26c3462f2ba33543ac1732b7a9701951fa760292153"
},
{
"path": "voices/ln/voice.json",
"size": 665,
"sha256": "58fed1e9707bb5e6eb6a225c932e17a61172c1a5f4b8752670655cf475c46207"
},
{
"path": "voices/lg/voice.onnx",
"size": 57770029,
"sha256": "ce21f335c77fdabcee5da2462dee5c25f86937dcb5581358ad0525e70dde8288"
},
{
"path": "voices/lg/voice.json",
"size": 666,
"sha256": "4ebec27323a13fdbf30ffb382c6178e2b03046f3a6a6a8b371e5c5d4e6ecefd2"
},
{
"path": "voices/om/voice.onnx",
"size": 57775407,
"sha256": "c37c01d81284159cd6923208bab7e99ea830891bd0b5f3269574079f05c97a89"
},
{
"path": "voices/om/voice.json",
"size": 786,
"sha256": "896e333a3b780ca16bd99a186c39779abd623e6486effb7658ee3cd388c6f451"
},
{
"path": "voices/sn/voice.onnx",
"size": 57770029,
"sha256": "ecccc14353f9637484c55c8af363a7c7d2a7858f4a21bb01a78c4dbed3fbb855"
},
{
"path": "voices/sn/voice.json",
"size": 662,
"sha256": "587d8667b76fe1548c2de4711f09afcd64791953c9dadb33d4eca828651648b8"
},
{
"path": "voices/ny/voice.onnx",
"size": 57770413,
"sha256": "0683c5ecd91960484f36f8eaa0a8fc4f7ee481bc6d94f43deacedb289c3a6882"
},
{
"path": "voices/ny/voice.json",
"size": 676,
"sha256": "5ad4e256170f611c92551885024a14eebb8adf95e730c18f4dfce392e157c098"
},
{
"path": "voices/nd/voice.onnx",
"size": 57777327,
"sha256": "1bdf764ea0af8c2ed58e9b00baa3d36b4ceb217c4b77ac39c4146c2e50197786"
},
{
"path": "voices/nd/voice.json",
"size": 834,
"sha256": "c79672cf3eb54449a09a2ac2f591a27368b8de29dc60ed7f6cbb5e0de93894f5"
},
{
"path": "lid/lang95.onnx",
"size": 16972591,
"sha256": "12a91f706ad6ca5a5eba4e84a96739d077e56f121ec71db86a752f62e218a227"
}
]
},
{
"id": "africa2b",
"name": "Best African translator",
"about": "Bigger African translation model: better wording, needs a phone with 12 GB of memory",
"required": false,
"default": false,
"files": [
{
"path": "africa/mt2b/model.gguf",
"size": 1488552000,
"sha256": "4987076acfdaca64558b8d446e3d7e3fdd84270a8ae6b6c0127c388ee1e758a9"
},
{
"path": "africa/mt2b/translator.json",
"size": 84,
"sha256": "9a56ed66a5f418b2cefb22fbc1c85d1ac42ec36606eadc949b84d66d38bcc156"
}
]
},
{
"id": "ja",
"name": "Japanese",
"about": "Hears Japanese (NVIDIA Parakeet), translates it to and from every language, speaks it",
"required": false,
"default": false,
"files": [
{
"path": "asia/ja/asr/model.int4.onnx",
"size": 406386777,
"sha256": "50cbf9dca8fcc5e73127411d17beee8a5ca65baabf448b7351091e2f4d7b41dc"
},
{
"path": "asia/ja/asr/tokens.txt",
"size": 28557,
"sha256": "732f64c53909f2620c713f4106b487d92e6f54a6915b3cd3d1dbd32f9f4f392a"
},
{
"path": "lid/lang95.onnx",
"size": 16972591,
"sha256": "12a91f706ad6ca5a5eba4e84a96739d077e56f121ec71db86a752f62e218a227"
}
]
},
{
"id": "zh",
"name": "Chinese",
"about": "Hears Mandarin Chinese (X-ASR), translates it to and from every language, speaks it (Kokoro)",
"required": false,
"default": false,
"files": [
{
"path": "asia/zh/asr/encoder.int8.onnx",
"size": 161015713,
"sha256": "7f6aa62056efd8af9da13e0faa81cd3f284d2fb2e3b63de56fd2dfd3450910dc"
},
{
"path": "asia/zh/asr/decoder.onnx",
"size": 11309084,
"sha256": "72f47405d3c1033bebccbef82f90071e7b4ba3e71b9c986f2b74244b25723aed"
},
{
"path": "asia/zh/asr/joiner.int8.onnx",
"size": 2581422,
"sha256": "aedb7fa697b2ab43f20499826fff7c997eea7d67db77be97769aeeeb726e63b3"
},
{
"path": "asia/zh/asr/tokens.txt",
"size": 58806,
"sha256": "b818a60878b9aae978cbb8ad594acbd403d76d1af2e31ef4197c84e2dbdba27c"
},
{
"path": "asia/zh/voice/model.int8.onnx",
"size": 114299010,
"sha256": "bda15858163726a492d02a9a727bc263551b86ac77f90812c4b30ff41d380e26"
},
{
"path": "asia/zh/voice/voices.bin",
"size": 5222400,
"sha256": "2064a309400607d361273058d7c6440b2318b3dac670cbe6c52b73d639595d57"
},
{
"path": "asia/zh/voice/tokens.txt",
"size": 1111,
"sha256": "931ab2df2400cd65d580a22402024c2347ced8ae9ea300e545144b1aacc48e14"
},
{
"path": "asia/zh/voice/lexicon-us-en.txt",
"size": 5956885,
"sha256": "7daaab53a181be9885b853a8582bf1838186317e5dadacbcef9c426d6fa0da14"
},
{
"path": "asia/zh/voice/lexicon-zh.txt",
"size": 2119465,
"sha256": "11111d8cd695fba2ace1367a1d0a708b586e6ef5c1f9be91da5d7eef129b651c"
},
{
"path": "lid/lang95.onnx",
"size": 16972591,
"sha256": "12a91f706ad6ca5a5eba4e84a96739d077e56f121ec71db86a752f62e218a227"
}
]
},
{
"id": "ko",
"name": "Korean",
"about": "Hears Korean (Meta Omnilingual ASR), translates it to and from every language, speaks it",
"required": false,
"default": false,
"files": [
{
"path": "africa/asr/model.int8.onnx",
"size": 365841453,
"sha256": "e3042b2f3b3ef0af2211bf99d2b4bf94a21f5ac0e9898827e7dd6d003a860e91"
},
{
"path": "africa/asr/tokens.txt",
"size": 90630,
"sha256": "7d99997ef207ff14c2cfe825f2aa037528ea250113cc3c6392bfe49326884ba6"
},
{
"path": "lid/lang95.onnx",
"size": 16972591,
"sha256": "12a91f706ad6ca5a5eba4e84a96739d077e56f121ec71db86a752f62e218a227"
}
]
}
]
}