AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16
hf AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16 2 sources, 2 claims · Watch
What each source says
| Property | Source | Said | Means here | ||||||
|---|---|---|---|---|---|---|---|---|---|
| Author author not compared | GGUF quantisations | Adit2Kreceipt
What the source handed over{
"_id": "6abfbb62bd9106023018731e",
"author": "Adit2K",
"cardData": {
"base_model": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"base_model_relation": "quantized",
"language": [
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu"
],
"license": "apache-2.0",
"license_link": "LICENSE",
"tags": [
"gguf",
"forced-alignment",
"word-timestamps",
"transcribe.cpp",
"qwen3-forced-aligner",
"experimental"
]
},
"createdAt": "2026-10-02T14:10:42.000Z",
"downloads": 115,
"gated": false,
"id": "Adit2K/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-gguf",
"lastModified": "2026-10-02T14:16:02.000Z",
"likes": 0,
"modelId": "Adit2K/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-gguf",
"private": false,
"sha": "0be3d6f946238b7a15f1747d19f83289813eb393",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "NOESIS-Qwen3-ForcedAligner-0.6B-112LANG-Q8_0.gguf"
},
{
"rfilename": "NOTICE"
},
{
"rfilename": "README.md"
}
],
"tags": [
"gguf",
"forced-alignment",
"word-timestamps",
"transcribe.cpp",
"qwen3-forced-aligner",
"experimental",
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu",
"arxiv:2601.21337",
"base_model:AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"base_model:quantized:AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"license:apache-2.0",
"region:us"
]
} | — | ||||||
| Author author not compared | Hugging Face models | AMAImediareceipt
What the source handed over{
"_asked": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"_id": "6a909def54c0bb8fd059f869",
"author": "AMAImedia",
"cardData": {
"base_model": [
"Qwen/Qwen3-ForcedAligner-0.6B"
],
"language": [
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu"
],
"library_name": "qwen-asr",
"license": "apache-2.0",
"license_link": "LICENSE",
"pipeline_tag": "automatic-speech-recognition",
"tags": [
"forced-alignment",
"timestamp-prediction",
"speech-text-alignment",
"aligner",
"qwen3",
"qwen3-asr",
"qwen3-omni",
"alibaba",
"nar",
"non-autoregressive",
"112-languages",
"multilingual",
"dubbing",
"subtitles",
"noesis",
"dhcf-fno",
"unified-training",
"lora-merged"
]
},
"config": {
"architectures": [
"Qwen3ASRForConditionalGeneration"
],
"model_type": "qwen3_asr",
"processor_config": {
"chat_template": "{%- set ns = namespace(system_text=\"\") -%}\n{%- for m in messages -%}\n {%- if m.role == 'system' -%}\n {%- if m.content is string -%}\n {%- set ns.system_text = ns.system_text + m.content -%}\n {%- else -%}\n {%- for c in m.content -%}\n {%- if c.type == 'text' and (c.text is defined) -%}\n {%- set ns.system_text = ns.system_text + c.text -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n\n{%- set ns2 = namespace(audio_tokens=\"\") -%}\n{%- for m in messages -%}\n {%- if m.content is not string -%}\n {%- for c in m.content -%}\n {%- if c.type == 'audio' or ('audio' in c) or ('audio_url' in c) -%}\n {%- set ns2.audio_tokens = ns2.audio_tokens + \"<|audio_start|><|audio_pad|><|audio_end|>\" -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n{%- endfor -%}\n\n{{- '<|im_start|>system\\n' + (ns.system_text if ns.system_text is string else '') + '<|im_end|>\\n' -}}\n{{- '<|im_start|>user\\n' + ns2.audio_tokens + '<|im_end|>\\n' -}}\n{%- if add_generation_prompt -%}\n{{- '<|im_start|>assistant\\n' -}}\n{%- endif -%}"
},
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-08-27T20:28:31.000Z",
"disabled": false,
"downloads": 208,
"gated": false,
"id": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"lastModified": "2026-09-29T16:09:56.000Z",
"library_name": "qwen-asr",
"likes": 1,
"model-index": null,
"modelId": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"pipeline_tag": "automatic-speech-recognition",
"private": false,
"safetensors": {
"parameters": {
"BF16": 917728896
},
"total": 917728896
},
"sha": "7979f38a4d60494dec1ad79cd24c1bb84ecc98bc",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "config.json.before_support_languages_112"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model.safetensors"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"qwen-asr",
"safetensors",
"qwen3_asr",
"forced-alignment",
"timestamp-prediction",
"speech-text-alignment",
"aligner",
"qwen3",
"qwen3-asr",
"qwen3-omni",
"alibaba",
"nar",
"non-autoregressive",
"112-languages",
"multilingual",
"dubbing",
"subtitles",
"noesis",
"dhcf-fno",
"unified-training",
"lora-merged",
"automatic-speech-recognition",
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu",
"arxiv:2601.21337",
"base_model:Qwen/Qwen3-ForcedAligner-0.6B",
"base_model:finetune:Qwen/Qwen3-ForcedAligner-0.6B",
"license:apache-2.0",
"region:us"
],
"usedStorage": 1835544544
} | — | ||||||
| Base base | GGUF quantisations | AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16receipt
What the source handed over{
"_id": "6abfbb62bd9106023018731e",
"author": "Adit2K",
"cardData": {
"base_model": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"base_model_relation": "quantized",
"language": [
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu"
],
"license": "apache-2.0",
"license_link": "LICENSE",
"tags": [
"gguf",
"forced-alignment",
"word-timestamps",
"transcribe.cpp",
"qwen3-forced-aligner",
"experimental"
]
},
"createdAt": "2026-10-02T14:10:42.000Z",
"downloads": 115,
"gated": false,
"id": "Adit2K/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-gguf",
"lastModified": "2026-10-02T14:16:02.000Z",
"likes": 0,
"modelId": "Adit2K/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-gguf",
"private": false,
"sha": "0be3d6f946238b7a15f1747d19f83289813eb393",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "NOESIS-Qwen3-ForcedAligner-0.6B-112LANG-Q8_0.gguf"
},
{
"rfilename": "NOTICE"
},
{
"rfilename": "README.md"
}
],
"tags": [
"gguf",
"forced-alignment",
"word-timestamps",
"transcribe.cpp",
"qwen3-forced-aligner",
"experimental",
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu",
"arxiv:2601.21337",
"base_model:AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"base_model:quantized:AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"license:apache-2.0",
"region:us"
]
} | — | ||||||
| Downloads downloads not compared | GGUF quantisations | 115receipt
What the source handed over{
"_id": "6abfbb62bd9106023018731e",
"author": "Adit2K",
"cardData": {
"base_model": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"base_model_relation": "quantized",
"language": [
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu"
],
"license": "apache-2.0",
"license_link": "LICENSE",
"tags": [
"gguf",
"forced-alignment",
"word-timestamps",
"transcribe.cpp",
"qwen3-forced-aligner",
"experimental"
]
},
"createdAt": "2026-10-02T14:10:42.000Z",
"downloads": 115,
"gated": false,
"id": "Adit2K/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-gguf",
"lastModified": "2026-10-02T14:16:02.000Z",
"likes": 0,
"modelId": "Adit2K/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-gguf",
"private": false,
"sha": "0be3d6f946238b7a15f1747d19f83289813eb393",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "NOESIS-Qwen3-ForcedAligner-0.6B-112LANG-Q8_0.gguf"
},
{
"rfilename": "NOTICE"
},
{
"rfilename": "README.md"
}
],
"tags": [
"gguf",
"forced-alignment",
"word-timestamps",
"transcribe.cpp",
"qwen3-forced-aligner",
"experimental",
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu",
"arxiv:2601.21337",
"base_model:AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"base_model:quantized:AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"license:apache-2.0",
"region:us"
]
} | — | ||||||
| Downloads downloads not compared | Hugging Face models | 208receipt
What the source handed over{
"_asked": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"_id": "6a909def54c0bb8fd059f869",
"author": "AMAImedia",
"cardData": {
"base_model": [
"Qwen/Qwen3-ForcedAligner-0.6B"
],
"language": [
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu"
],
"library_name": "qwen-asr",
"license": "apache-2.0",
"license_link": "LICENSE",
"pipeline_tag": "automatic-speech-recognition",
"tags": [
"forced-alignment",
"timestamp-prediction",
"speech-text-alignment",
"aligner",
"qwen3",
"qwen3-asr",
"qwen3-omni",
"alibaba",
"nar",
"non-autoregressive",
"112-languages",
"multilingual",
"dubbing",
"subtitles",
"noesis",
"dhcf-fno",
"unified-training",
"lora-merged"
]
},
"config": {
"architectures": [
"Qwen3ASRForConditionalGeneration"
],
"model_type": "qwen3_asr",
"processor_config": {
"chat_template": "{%- set ns = namespace(system_text=\"\") -%}\n{%- for m in messages -%}\n {%- if m.role == 'system' -%}\n {%- if m.content is string -%}\n {%- set ns.system_text = ns.system_text + m.content -%}\n {%- else -%}\n {%- for c in m.content -%}\n {%- if c.type == 'text' and (c.text is defined) -%}\n {%- set ns.system_text = ns.system_text + c.text -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n\n{%- set ns2 = namespace(audio_tokens=\"\") -%}\n{%- for m in messages -%}\n {%- if m.content is not string -%}\n {%- for c in m.content -%}\n {%- if c.type == 'audio' or ('audio' in c) or ('audio_url' in c) -%}\n {%- set ns2.audio_tokens = ns2.audio_tokens + \"<|audio_start|><|audio_pad|><|audio_end|>\" -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n{%- endfor -%}\n\n{{- '<|im_start|>system\\n' + (ns.system_text if ns.system_text is string else '') + '<|im_end|>\\n' -}}\n{{- '<|im_start|>user\\n' + ns2.audio_tokens + '<|im_end|>\\n' -}}\n{%- if add_generation_prompt -%}\n{{- '<|im_start|>assistant\\n' -}}\n{%- endif -%}"
},
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-08-27T20:28:31.000Z",
"disabled": false,
"downloads": 208,
"gated": false,
"id": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"lastModified": "2026-09-29T16:09:56.000Z",
"library_name": "qwen-asr",
"likes": 1,
"model-index": null,
"modelId": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"pipeline_tag": "automatic-speech-recognition",
"private": false,
"safetensors": {
"parameters": {
"BF16": 917728896
},
"total": 917728896
},
"sha": "7979f38a4d60494dec1ad79cd24c1bb84ecc98bc",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "config.json.before_support_languages_112"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model.safetensors"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"qwen-asr",
"safetensors",
"qwen3_asr",
"forced-alignment",
"timestamp-prediction",
"speech-text-alignment",
"aligner",
"qwen3",
"qwen3-asr",
"qwen3-omni",
"alibaba",
"nar",
"non-autoregressive",
"112-languages",
"multilingual",
"dubbing",
"subtitles",
"noesis",
"dhcf-fno",
"unified-training",
"lora-merged",
"automatic-speech-recognition",
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu",
"arxiv:2601.21337",
"base_model:Qwen/Qwen3-ForcedAligner-0.6B",
"base_model:finetune:Qwen/Qwen3-ForcedAligner-0.6B",
"license:apache-2.0",
"region:us"
],
"usedStorage": 1835544544
} | — | ||||||
| Gated gated | Hugging Face models | falsereceipt
What the source handed over{
"_asked": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"_id": "6a909def54c0bb8fd059f869",
"author": "AMAImedia",
"cardData": {
"base_model": [
"Qwen/Qwen3-ForcedAligner-0.6B"
],
"language": [
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu"
],
"library_name": "qwen-asr",
"license": "apache-2.0",
"license_link": "LICENSE",
"pipeline_tag": "automatic-speech-recognition",
"tags": [
"forced-alignment",
"timestamp-prediction",
"speech-text-alignment",
"aligner",
"qwen3",
"qwen3-asr",
"qwen3-omni",
"alibaba",
"nar",
"non-autoregressive",
"112-languages",
"multilingual",
"dubbing",
"subtitles",
"noesis",
"dhcf-fno",
"unified-training",
"lora-merged"
]
},
"config": {
"architectures": [
"Qwen3ASRForConditionalGeneration"
],
"model_type": "qwen3_asr",
"processor_config": {
"chat_template": "{%- set ns = namespace(system_text=\"\") -%}\n{%- for m in messages -%}\n {%- if m.role == 'system' -%}\n {%- if m.content is string -%}\n {%- set ns.system_text = ns.system_text + m.content -%}\n {%- else -%}\n {%- for c in m.content -%}\n {%- if c.type == 'text' and (c.text is defined) -%}\n {%- set ns.system_text = ns.system_text + c.text -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n\n{%- set ns2 = namespace(audio_tokens=\"\") -%}\n{%- for m in messages -%}\n {%- if m.content is not string -%}\n {%- for c in m.content -%}\n {%- if c.type == 'audio' or ('audio' in c) or ('audio_url' in c) -%}\n {%- set ns2.audio_tokens = ns2.audio_tokens + \"<|audio_start|><|audio_pad|><|audio_end|>\" -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n{%- endfor -%}\n\n{{- '<|im_start|>system\\n' + (ns.system_text if ns.system_text is string else '') + '<|im_end|>\\n' -}}\n{{- '<|im_start|>user\\n' + ns2.audio_tokens + '<|im_end|>\\n' -}}\n{%- if add_generation_prompt -%}\n{{- '<|im_start|>assistant\\n' -}}\n{%- endif -%}"
},
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-08-27T20:28:31.000Z",
"disabled": false,
"downloads": 208,
"gated": false,
"id": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"lastModified": "2026-09-29T16:09:56.000Z",
"library_name": "qwen-asr",
"likes": 1,
"model-index": null,
"modelId": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"pipeline_tag": "automatic-speech-recognition",
"private": false,
"safetensors": {
"parameters": {
"BF16": 917728896
},
"total": 917728896
},
"sha": "7979f38a4d60494dec1ad79cd24c1bb84ecc98bc",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "config.json.before_support_languages_112"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model.safetensors"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"qwen-asr",
"safetensors",
"qwen3_asr",
"forced-alignment",
"timestamp-prediction",
"speech-text-alignment",
"aligner",
"qwen3",
"qwen3-asr",
"qwen3-omni",
"alibaba",
"nar",
"non-autoregressive",
"112-languages",
"multilingual",
"dubbing",
"subtitles",
"noesis",
"dhcf-fno",
"unified-training",
"lora-merged",
"automatic-speech-recognition",
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu",
"arxiv:2601.21337",
"base_model:Qwen/Qwen3-ForcedAligner-0.6B",
"base_model:finetune:Qwen/Qwen3-ForcedAligner-0.6B",
"license:apache-2.0",
"region:us"
],
"usedStorage": 1835544544
} | — | ||||||
| Licence licence | GGUF quantisations | apache-2.0receipt
What the source handed over{
"_id": "6abfbb62bd9106023018731e",
"author": "Adit2K",
"cardData": {
"base_model": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"base_model_relation": "quantized",
"language": [
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu"
],
"license": "apache-2.0",
"license_link": "LICENSE",
"tags": [
"gguf",
"forced-alignment",
"word-timestamps",
"transcribe.cpp",
"qwen3-forced-aligner",
"experimental"
]
},
"createdAt": "2026-10-02T14:10:42.000Z",
"downloads": 115,
"gated": false,
"id": "Adit2K/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-gguf",
"lastModified": "2026-10-02T14:16:02.000Z",
"likes": 0,
"modelId": "Adit2K/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-gguf",
"private": false,
"sha": "0be3d6f946238b7a15f1747d19f83289813eb393",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "NOESIS-Qwen3-ForcedAligner-0.6B-112LANG-Q8_0.gguf"
},
{
"rfilename": "NOTICE"
},
{
"rfilename": "README.md"
}
],
"tags": [
"gguf",
"forced-alignment",
"word-timestamps",
"transcribe.cpp",
"qwen3-forced-aligner",
"experimental",
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu",
"arxiv:2601.21337",
"base_model:AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"base_model:quantized:AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"license:apache-2.0",
"region:us"
]
} | — | ||||||
| Licence licence | Hugging Face models | apache-2.0receipt
What the source handed over{
"_asked": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"_id": "6a909def54c0bb8fd059f869",
"author": "AMAImedia",
"cardData": {
"base_model": [
"Qwen/Qwen3-ForcedAligner-0.6B"
],
"language": [
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu"
],
"library_name": "qwen-asr",
"license": "apache-2.0",
"license_link": "LICENSE",
"pipeline_tag": "automatic-speech-recognition",
"tags": [
"forced-alignment",
"timestamp-prediction",
"speech-text-alignment",
"aligner",
"qwen3",
"qwen3-asr",
"qwen3-omni",
"alibaba",
"nar",
"non-autoregressive",
"112-languages",
"multilingual",
"dubbing",
"subtitles",
"noesis",
"dhcf-fno",
"unified-training",
"lora-merged"
]
},
"config": {
"architectures": [
"Qwen3ASRForConditionalGeneration"
],
"model_type": "qwen3_asr",
"processor_config": {
"chat_template": "{%- set ns = namespace(system_text=\"\") -%}\n{%- for m in messages -%}\n {%- if m.role == 'system' -%}\n {%- if m.content is string -%}\n {%- set ns.system_text = ns.system_text + m.content -%}\n {%- else -%}\n {%- for c in m.content -%}\n {%- if c.type == 'text' and (c.text is defined) -%}\n {%- set ns.system_text = ns.system_text + c.text -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n\n{%- set ns2 = namespace(audio_tokens=\"\") -%}\n{%- for m in messages -%}\n {%- if m.content is not string -%}\n {%- for c in m.content -%}\n {%- if c.type == 'audio' or ('audio' in c) or ('audio_url' in c) -%}\n {%- set ns2.audio_tokens = ns2.audio_tokens + \"<|audio_start|><|audio_pad|><|audio_end|>\" -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n{%- endfor -%}\n\n{{- '<|im_start|>system\\n' + (ns.system_text if ns.system_text is string else '') + '<|im_end|>\\n' -}}\n{{- '<|im_start|>user\\n' + ns2.audio_tokens + '<|im_end|>\\n' -}}\n{%- if add_generation_prompt -%}\n{{- '<|im_start|>assistant\\n' -}}\n{%- endif -%}"
},
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-08-27T20:28:31.000Z",
"disabled": false,
"downloads": 208,
"gated": false,
"id": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"lastModified": "2026-09-29T16:09:56.000Z",
"library_name": "qwen-asr",
"likes": 1,
"model-index": null,
"modelId": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"pipeline_tag": "automatic-speech-recognition",
"private": false,
"safetensors": {
"parameters": {
"BF16": 917728896
},
"total": 917728896
},
"sha": "7979f38a4d60494dec1ad79cd24c1bb84ecc98bc",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "config.json.before_support_languages_112"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model.safetensors"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"qwen-asr",
"safetensors",
"qwen3_asr",
"forced-alignment",
"timestamp-prediction",
"speech-text-alignment",
"aligner",
"qwen3",
"qwen3-asr",
"qwen3-omni",
"alibaba",
"nar",
"non-autoregressive",
"112-languages",
"multilingual",
"dubbing",
"subtitles",
"noesis",
"dhcf-fno",
"unified-training",
"lora-merged",
"automatic-speech-recognition",
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu",
"arxiv:2601.21337",
"base_model:Qwen/Qwen3-ForcedAligner-0.6B",
"base_model:finetune:Qwen/Qwen3-ForcedAligner-0.6B",
"license:apache-2.0",
"region:us"
],
"usedStorage": 1835544544
} | — | ||||||
| Likes likes not compared | GGUF quantisations | 0receipt
What the source handed over{
"_id": "6abfbb62bd9106023018731e",
"author": "Adit2K",
"cardData": {
"base_model": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"base_model_relation": "quantized",
"language": [
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu"
],
"license": "apache-2.0",
"license_link": "LICENSE",
"tags": [
"gguf",
"forced-alignment",
"word-timestamps",
"transcribe.cpp",
"qwen3-forced-aligner",
"experimental"
]
},
"createdAt": "2026-10-02T14:10:42.000Z",
"downloads": 115,
"gated": false,
"id": "Adit2K/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-gguf",
"lastModified": "2026-10-02T14:16:02.000Z",
"likes": 0,
"modelId": "Adit2K/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-gguf",
"private": false,
"sha": "0be3d6f946238b7a15f1747d19f83289813eb393",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "NOESIS-Qwen3-ForcedAligner-0.6B-112LANG-Q8_0.gguf"
},
{
"rfilename": "NOTICE"
},
{
"rfilename": "README.md"
}
],
"tags": [
"gguf",
"forced-alignment",
"word-timestamps",
"transcribe.cpp",
"qwen3-forced-aligner",
"experimental",
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu",
"arxiv:2601.21337",
"base_model:AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"base_model:quantized:AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"license:apache-2.0",
"region:us"
]
} | — | ||||||
| Likes likes not compared | Hugging Face models | 1receipt
What the source handed over{
"_asked": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"_id": "6a909def54c0bb8fd059f869",
"author": "AMAImedia",
"cardData": {
"base_model": [
"Qwen/Qwen3-ForcedAligner-0.6B"
],
"language": [
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu"
],
"library_name": "qwen-asr",
"license": "apache-2.0",
"license_link": "LICENSE",
"pipeline_tag": "automatic-speech-recognition",
"tags": [
"forced-alignment",
"timestamp-prediction",
"speech-text-alignment",
"aligner",
"qwen3",
"qwen3-asr",
"qwen3-omni",
"alibaba",
"nar",
"non-autoregressive",
"112-languages",
"multilingual",
"dubbing",
"subtitles",
"noesis",
"dhcf-fno",
"unified-training",
"lora-merged"
]
},
"config": {
"architectures": [
"Qwen3ASRForConditionalGeneration"
],
"model_type": "qwen3_asr",
"processor_config": {
"chat_template": "{%- set ns = namespace(system_text=\"\") -%}\n{%- for m in messages -%}\n {%- if m.role == 'system' -%}\n {%- if m.content is string -%}\n {%- set ns.system_text = ns.system_text + m.content -%}\n {%- else -%}\n {%- for c in m.content -%}\n {%- if c.type == 'text' and (c.text is defined) -%}\n {%- set ns.system_text = ns.system_text + c.text -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n\n{%- set ns2 = namespace(audio_tokens=\"\") -%}\n{%- for m in messages -%}\n {%- if m.content is not string -%}\n {%- for c in m.content -%}\n {%- if c.type == 'audio' or ('audio' in c) or ('audio_url' in c) -%}\n {%- set ns2.audio_tokens = ns2.audio_tokens + \"<|audio_start|><|audio_pad|><|audio_end|>\" -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n{%- endfor -%}\n\n{{- '<|im_start|>system\\n' + (ns.system_text if ns.system_text is string else '') + '<|im_end|>\\n' -}}\n{{- '<|im_start|>user\\n' + ns2.audio_tokens + '<|im_end|>\\n' -}}\n{%- if add_generation_prompt -%}\n{{- '<|im_start|>assistant\\n' -}}\n{%- endif -%}"
},
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-08-27T20:28:31.000Z",
"disabled": false,
"downloads": 208,
"gated": false,
"id": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"lastModified": "2026-09-29T16:09:56.000Z",
"library_name": "qwen-asr",
"likes": 1,
"model-index": null,
"modelId": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"pipeline_tag": "automatic-speech-recognition",
"private": false,
"safetensors": {
"parameters": {
"BF16": 917728896
},
"total": 917728896
},
"sha": "7979f38a4d60494dec1ad79cd24c1bb84ecc98bc",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "config.json.before_support_languages_112"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model.safetensors"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"qwen-asr",
"safetensors",
"qwen3_asr",
"forced-alignment",
"timestamp-prediction",
"speech-text-alignment",
"aligner",
"qwen3",
"qwen3-asr",
"qwen3-omni",
"alibaba",
"nar",
"non-autoregressive",
"112-languages",
"multilingual",
"dubbing",
"subtitles",
"noesis",
"dhcf-fno",
"unified-training",
"lora-merged",
"automatic-speech-recognition",
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu",
"arxiv:2601.21337",
"base_model:Qwen/Qwen3-ForcedAligner-0.6B",
"base_model:finetune:Qwen/Qwen3-ForcedAligner-0.6B",
"license:apache-2.0",
"region:us"
],
"usedStorage": 1835544544
} | — | ||||||
| Task task | Hugging Face models | automatic-speech-recognitionreceipt
What the source handed over{
"_asked": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"_id": "6a909def54c0bb8fd059f869",
"author": "AMAImedia",
"cardData": {
"base_model": [
"Qwen/Qwen3-ForcedAligner-0.6B"
],
"language": [
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu"
],
"library_name": "qwen-asr",
"license": "apache-2.0",
"license_link": "LICENSE",
"pipeline_tag": "automatic-speech-recognition",
"tags": [
"forced-alignment",
"timestamp-prediction",
"speech-text-alignment",
"aligner",
"qwen3",
"qwen3-asr",
"qwen3-omni",
"alibaba",
"nar",
"non-autoregressive",
"112-languages",
"multilingual",
"dubbing",
"subtitles",
"noesis",
"dhcf-fno",
"unified-training",
"lora-merged"
]
},
"config": {
"architectures": [
"Qwen3ASRForConditionalGeneration"
],
"model_type": "qwen3_asr",
"processor_config": {
"chat_template": "{%- set ns = namespace(system_text=\"\") -%}\n{%- for m in messages -%}\n {%- if m.role == 'system' -%}\n {%- if m.content is string -%}\n {%- set ns.system_text = ns.system_text + m.content -%}\n {%- else -%}\n {%- for c in m.content -%}\n {%- if c.type == 'text' and (c.text is defined) -%}\n {%- set ns.system_text = ns.system_text + c.text -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n\n{%- set ns2 = namespace(audio_tokens=\"\") -%}\n{%- for m in messages -%}\n {%- if m.content is not string -%}\n {%- for c in m.content -%}\n {%- if c.type == 'audio' or ('audio' in c) or ('audio_url' in c) -%}\n {%- set ns2.audio_tokens = ns2.audio_tokens + \"<|audio_start|><|audio_pad|><|audio_end|>\" -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n{%- endfor -%}\n\n{{- '<|im_start|>system\\n' + (ns.system_text if ns.system_text is string else '') + '<|im_end|>\\n' -}}\n{{- '<|im_start|>user\\n' + ns2.audio_tokens + '<|im_end|>\\n' -}}\n{%- if add_generation_prompt -%}\n{{- '<|im_start|>assistant\\n' -}}\n{%- endif -%}"
},
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-08-27T20:28:31.000Z",
"disabled": false,
"downloads": 208,
"gated": false,
"id": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"lastModified": "2026-09-29T16:09:56.000Z",
"library_name": "qwen-asr",
"likes": 1,
"model-index": null,
"modelId": "AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16",
"pipeline_tag": "automatic-speech-recognition",
"private": false,
"safetensors": {
"parameters": {
"BF16": 917728896
},
"total": 917728896
},
"sha": "7979f38a4d60494dec1ad79cd24c1bb84ecc98bc",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "config.json.before_support_languages_112"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model.safetensors"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"qwen-asr",
"safetensors",
"qwen3_asr",
"forced-alignment",
"timestamp-prediction",
"speech-text-alignment",
"aligner",
"qwen3",
"qwen3-asr",
"qwen3-omni",
"alibaba",
"nar",
"non-autoregressive",
"112-languages",
"multilingual",
"dubbing",
"subtitles",
"noesis",
"dhcf-fno",
"unified-training",
"lora-merged",
"automatic-speech-recognition",
"af",
"am",
"ar",
"as",
"ast",
"az",
"be",
"bg",
"bn",
"bs",
"ca",
"ceb",
"ckb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fil",
"fr",
"ga",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kam",
"kea",
"kk",
"km",
"kmr",
"kn",
"ko",
"ky",
"lb",
"lg",
"ln",
"lo",
"lt",
"luo",
"lv",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"mvy",
"my",
"ne",
"nl",
"no",
"nso",
"ny",
"oc",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qxp",
"ro",
"ru",
"rw",
"sd",
"sk",
"skr",
"sl",
"sn",
"so",
"sr",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tr",
"ug",
"uk",
"umb",
"ur",
"uz",
"vi",
"wo",
"xh",
"yo",
"yue",
"zh",
"zu",
"arxiv:2601.21337",
"base_model:Qwen/Qwen3-ForcedAligner-0.6B",
"base_model:finetune:Qwen/Qwen3-ForcedAligner-0.6B",
"license:apache-2.0",
"region:us"
],
"usedStorage": 1835544544
} | — |
model
| AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16 zetlyn/models-hf · 2026-08-27 | author AMAImedia downloads 208 gated false licence apache-2.0 likes 1 task automatic-speech-recognition | source |
quantisation
| Adit2K/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-gguf zetlyn/models-gguf · 2026-10-02 | author Adit2K base AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16 downloads 115 licence apache-2.0 likes 0 | source |