{"v":1,"id":"model:hf:handy-computer/whisper-small-gguf","slug":"model-handy-computer-whisper-small-gguf","kind":"model","category":"speech","title":"whisper-small-gguf","summary":"GGUF conversions of openai/whisper-small for use with transcribe.cpp.","source":{"provider":"hf","ref":"handy-computer/whisper-small-gguf","url":"https://huggingface.co/handy-computer/whisper-small-gguf","rev":"a2073177cb69bd74b9ca9460b852d17fbfd5d68c","fetchedAt":"2026-10-02T21:00:09.553Z","etag":"W/\"1979-D5Q39u+/smTxZTlOEXyPT9TgvGg\""},"author":{"name":"handy-computer","url":"https://huggingface.co/handy-computer"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":46305,"downloadsWeek":15195,"likes":0,"takenAt":"2026-10-02T21:00:09.553Z"},"tags":["transcribe.cpp","gguf","asr","speech-to-text","whisper","openai","automatic-speech-recognition","af","am","ar","as","az","ba","be","bg","bn","bo","br","bs","ca","cs","cy","da","de","el","en","es","et","eu","fa","fi","fo","fr","gl","gu","haw","ha","he","hi","hr"],"pipeline":"automatic-speech-recognition","links":{"github":"ggml-org/whisper.cpp","npm":"nodejs-whisper"},"updatedAt":"2026-09-15T07:05:48.000Z","collectedAt":"2026-10-02T21:00:09.553Z","review":{"numbers":["46,305 downloads on Hugging Face","0 likes","license apache-2.0","0.2 GB for whisper-small-Q4_K_M.gguf","15,195 npm downloads a week for nodejs-whisper","latest nodejs-whisper@0.3.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:00:09.553Z","http":200},"description":"# whisper-small: transcribe.cpp GGUF\n\nGGUF conversions of [openai/whisper-small](https://huggingface.co/openai/whisper-small) for use\nwith [transcribe.cpp](https://github.com/handy-computer/transcribe.cpp).\n\nPorted from upstream commit\n[973afd2](https://huggingface.co/openai/whisper-small/commit/973afd2),\npinned 2026-04-25.\nValidated against the transformers reference at transcribe.cpp commit\n[5.6.1](https://github.com/handy-computer/transcribe.cpp/tree/5.6.1)\non 2026-04-26.\n\nOpenAI Whisper small — converted to GGUF for transcribe.cpp. Multilingual transcription, language detection, and speech translation (audio in any supported language → English text). Encoder-decoder transformer; 30-second windows with chunked long-form decoding.\n\n## Downloads\n\n| Quantization | Download | Size | WER (LibriSpeech test-clean) |\n| --- | --- | ---: | ---: |\n| F32 | [whisper-small-F32.gguf](https://huggingface.co/handy-computer/whisper-small-gguf/resolve/main/whisper-small-F32.gguf) | 969 MB | 3.34% |\n| F16 | [whisper-small-F16.gguf](https://huggingface.co/handy-computer/whisper-small-gguf/resolve/main/whisper-small-F16.gguf) | 493 MB | 3.33% |\n| Q8_0 | [whisper-small-Q8_0.gguf](https://huggingface.co/handy-computer/whisper-small-gguf/resolve/main/whisper-small-Q8_0.gguf) | 270 MB | 3.33% |\n| Q6_K | [whisper-small-Q6_K.gguf](https://huggingface.co/handy-computer/whisper-small-gguf/resolve/main/whisper-small-Q6_K.gguf) | 212 MB | 3.33% |\n| Q5_K_M | [whisper-small-Q5_K_M.gguf](https://huggingface.co/handy-computer/whisper-small-gguf/resolve/main/whisper-small-Q5_K_M.gguf) | 194 MB | 3.37% |\n| Q4_K_M | [whisper-small-Q4_K_M.gguf](https://huggingface.co/handy-computer/whisper-small-gguf/resolve/main/whisper-small-Q4_K_M.gguf) | 172 MB | 3.40% |\n\nWER on the full LibriSpeech test-clean split (2,620 utterances), batch size 1, timestamps none. Figures without a commit were published before provenance was recorded.\n\nOpenAI's se…\n\nSource: https://huggingface.co/handy-computer/whisper-small-gguf","install":{"kind":"model","hfId":"handy-computer/whisper-small-gguf","gated":false,"format":"gguf","files":[{"name":"whisper-small-F16.gguf","size":492888480,"quant":"F16","sha256":"bef65e1ac9d012269453243243aac0d0f67792693ba6c99b584a124e0ee326fc"},{"name":"whisper-small-F32.gguf","size":968914848,"quant":"F32","sha256":"6bc797078fdddcc890999130dfc33dfc30d82de5a9115a840ec73853262a9d21"},{"name":"whisper-small-Q4_K_M.gguf","size":171630656,"quant":"Q4_K_M","sha256":"b204d2005a3e5d4fe6153bd61e5e8b32e757ff7b017ac8f61c6f051c2f80e939"},{"name":"whisper-small-Q5_K_M.gguf","size":193749056,"quant":"Q5_K_M","sha256":"326cd00c3e7217c751667c7c1600eaf7e0de174e186ca2c16b4bf590251c3c3b"},{"name":"whisper-small-Q6_K.gguf","size":212107328,"quant":"Q6_K","sha256":"4d14215a972101fff787fc59e30b908ee511c725600317e02c9032cb8799f32d"},{"name":"whisper-small-Q8_0.gguf","size":269751136,"quant":"Q8_0","sha256":"9b9c8811bbcc82a7766f0fb0925614bdacb0923b2cc630daeac17108b655b860"}],"totalBytes":2309041504,"suggestedFile":"whisper-small-Q4_K_M.gguf","requirements":{"ramGb":1,"diskBytes":171630656,"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/whisper-small-gguf"}}