{"v":1,"id":"model:hf:handy-computer/canary-1b-v2-gguf","slug":"model-handy-computer-canary-1b-v2-gguf","kind":"model","category":"speech","title":"canary-1b-v2-gguf","summary":"GGUF conversions of nvidia/canary-1b-v2 for use with transcribe.cpp.","source":{"provider":"hf","ref":"handy-computer/canary-1b-v2-gguf","url":"https://huggingface.co/handy-computer/canary-1b-v2-gguf","rev":"e2d8e6d7f2accc1259dc5497b517b4083047e44b","fetchedAt":"2026-10-02T20:59:48.537Z","etag":"W/\"10fc-2VKGVMKT8MeVep9OOibhgCOhjtw\""},"author":{"name":"handy-computer","url":"https://huggingface.co/handy-computer"},"license":{"spdx":"cc-by-4.0","raw":"cc-by-4.0","open":true},"metrics":{"downloads":90002,"likes":1,"takenAt":"2026-10-02T20:59:48.537Z"},"tags":["transcribe.cpp","gguf","asr","speech-to-text","canary","multitask-aed","encoder-decoder","multilingual","translation","automatic-speech-recognition","bg","hr","cs","da","nl","en","et","fi","fr","de","el","hu","it","lv","lt","mt","pl","pt","ro","sk","sl","es","sv","ru","uk"],"pipeline":"automatic-speech-recognition","links":{"github":"NVIDIA-NeMo/NeMo"},"updatedAt":"2026-09-15T07:05:29.000Z","collectedAt":"2026-10-02T20:59:48.537Z","review":{"numbers":["90,002 downloads on Hugging Face","1 likes","license cc-by-4.0","0.7 GB for canary-1b-v2-Q4_K_M.gguf"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:48.537Z","http":200},"description":"# canary-1b-v2: transcribe.cpp GGUF\n\nGGUF conversions of [nvidia/canary-1b-v2](https://huggingface.co/nvidia/canary-1b-v2) for use\nwith [transcribe.cpp](https://github.com/handy-computer/transcribe.cpp).\n\nPorted from upstream commit\n[87bc526](https://huggingface.co/nvidia/canary-1b-v2/commit/87bc526),\npinned 2026-05-08.\nValidated against the NeMo reference at transcribe.cpp commit\n[db53eda](https://github.com/handy-computer/transcribe.cpp/tree/db53eda)\non 2026-05-08.\n\nOffline multilingual speech-to-text and translation across 25 European\nlanguages. A 978M-parameter multitask AED with a 32-layer FastConformer\nencoder and an 8-layer Transformer decoder. Supports automatic speech\nrecognition for any of the 25 supported languages, plus translation\nbetween supported language pairs (per the upstream model card). Takes\na 16 kHz mono WAV and produces a transcript. Not a streaming model;\nword and segment timestamps from the upstream model are not exposed in\nthe v1 port.\n\n## Downloads\n\n| Quantization | Download | Size | WER (LibriSpeech test-clean) |\n| --- | --- | ---: | ---: |\n| F32 | [canary-1b-v2-F32.gguf](https://huggingface.co/handy-computer/canary-1b-v2-gguf/resolve/main/canary-1b-v2-F32.gguf) | 3.92 GB | 1.92% |\n| F16 | [canary-1b-v2-F16.gguf](https://huggingface.co/handy-computer/canary-1b-v2-gguf/resolve/main/canary-1b-v2-F16.gguf) | 1.97 GB | 1.92% |\n| Q8_0 | [canary-1b-v2-Q8_0.gguf](https://huggingface.co/handy-computer/canary-1b-v2-gguf/resolve/main/canary-1b-v2-Q8_0.gguf) | 1.14 GB | 1.91% |\n| Q6_K | [canary-1b-v2-Q6_K.gguf](https://huggingface.co/handy-computer/canary-1b-v2-gguf/resolve/main/canary-1b-v2-Q6_K.gguf) | 932 MB | 1.94% |\n| Q5_K_M | [canary-1b-v2-Q5_K_M.gguf](https://huggingface.co/handy-computer/canary-1b-v2-gguf/resolve/main/canary-1b-v2-Q5_K_M.gguf) | 837 MB | 1.93% |\n| Q4_K_M | [canary-1b-v2-Q4_K_M.gguf](https://huggingface.co/handy-computer/canary-1b-v2-gguf/resolve/main/canary-1b…\n\nSource: https://huggingface.co/handy-computer/canary-1b-v2-gguf","install":{"kind":"model","hfId":"handy-computer/canary-1b-v2-gguf","gated":false,"format":"gguf","files":[{"name":"canary-1b-v2-F16.gguf","size":1966111456,"quant":"F16","sha256":"eadda53cd1652d65cd12ff7ac4b7dc64cba1ce9837aae0c86e4222e8db89e320"},{"name":"canary-1b-v2-F32.gguf","size":3920657120,"quant":"F32","sha256":"b0b48b62b2c68f2779c49481de102715c5eaadbe084bca7fdddc7912f9c20e8b"},{"name":"canary-1b-v2-Q4_K_M.gguf","size":735476448,"quant":"Q4_K_M","sha256":"49e0a67e219bec95a254c2348460b6350e75a7ac6f93a131e48244b4c7cb53b9"},{"name":"canary-1b-v2-Q5_K_M.gguf","size":836664032,"quant":"Q5_K_M","sha256":"9c3a893c93795438baf9b4b1c853c39b60316c3a0d259a3ba6e284712f5ddb71"},{"name":"canary-1b-v2-Q6_K.gguf","size":931986144,"quant":"Q6_K","sha256":"6567c2d601fccacf9809fc230edefde05728340f65860bbe91cfd72d0a5eea9d"},{"name":"canary-1b-v2-Q8_0.gguf","size":1144290016,"quant":"Q8_0","sha256":"224f83d1bc487b3303b495a7d6874912fdece93de19d1a04b550829c30a5d289"}],"totalBytes":9535185216,"suggestedFile":"canary-1b-v2-Q4_K_M.gguf","requirements":{"ramGb":2,"diskBytes":735476448,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["whisper.cpp"],"command":"lsh models install hf:handy-computer/canary-1b-v2-gguf"}}