{"v":1,"id":"model:hf:handy-computer/whisper-medium-gguf","slug":"model-handy-computer-whisper-medium-gguf","kind":"model","category":"speech","title":"whisper-medium-gguf","summary":"GGUF conversions of openai/whisper-medium for use with transcribe.cpp.","source":{"provider":"hf","ref":"handy-computer/whisper-medium-gguf","url":"https://huggingface.co/handy-computer/whisper-medium-gguf","rev":"835ad19fff976143d650e35113a6544980cbd983","fetchedAt":"2026-10-02T20:59:12.657Z","etag":"W/\"197f-5UE+thaf8pnLdXsBE9mc+sxEE8E\""},"author":{"name":"handy-computer","url":"https://huggingface.co/handy-computer"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":546249,"downloadsWeek":15195,"likes":0,"takenAt":"2026-10-02T20:59:12.657Z"},"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":"2026-09-15T07:05:47.000Z","collectedAt":"2026-10-02T20:59:12.657Z","review":{"numbers":["546,249 downloads on Hugging Face","0 likes","license apache-2.0","0.5 GB for whisper-medium-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":"2026-10-02T20:59:12.657Z","http":200},"description":"# whisper-medium: transcribe.cpp GGUF\n\nGGUF conversions of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) for use\nwith [transcribe.cpp](https://github.com/handy-computer/transcribe.cpp).\n\nPorted from upstream commit\n[abdf7c3](https://huggingface.co/openai/whisper-medium/commit/abdf7c3),\npinned 2026-04-25.\nValidated against the transformers reference at transcribe.cpp commit\n[0a26478](https://github.com/handy-computer/transcribe.cpp/tree/0a26478)\non 2026-09-13.\n\nOpenAI Whisper medium — 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-medium-F32.gguf](https://huggingface.co/handy-computer/whisper-medium-gguf/resolve/main/whisper-medium-F32.gguf) | 3.06 GB | 2.64% |\n| F16 | [whisper-medium-F16.gguf](https://huggingface.co/handy-computer/whisper-medium-gguf/resolve/main/whisper-medium-F16.gguf) | 1.54 GB | 2.63% |\n| Q8_0 | [whisper-medium-Q8_0.gguf](https://huggingface.co/handy-computer/whisper-medium-gguf/resolve/main/whisper-medium-Q8_0.gguf) | 832 MB | 2.64% |\n| Q6_K | [whisper-medium-Q6_K.gguf](https://huggingface.co/handy-computer/whisper-medium-gguf/resolve/main/whisper-medium-Q6_K.gguf) | 648 MB | 2.59% |\n| Q5_K_M | [whisper-medium-Q5_K_M.gguf](https://huggingface.co/handy-computer/whisper-medium-gguf/resolve/main/whisper-medium-Q5_K_M.gguf) | 583 MB | 2.62% |\n| Q4_K_M | [whisper-medium-Q4_K_M.gguf](https://huggingface.co/handy-computer/whisper-medium-gguf/resolve/main/whisper-medium-Q4_K_M.gguf) | 504 MB | 2.59% |\n\nWER on the full LibriSpeech test-clean split (2,620 utterances), batch size 1, timestamps none. Figures without a commit were published before provena…\n\nSource: https://huggingface.co/handy-computer/whisper-medium-gguf","install":{"kind":"model","hfId":"handy-computer/whisper-medium-gguf","gated":false,"format":"gguf","files":[{"name":"whisper-medium-F16.gguf","size":1541931424,"quant":"F16","sha256":"62338e5194cb9ccc6734adf6f42694805a98a158028b2022e39ec060559bd517"},{"name":"whisper-medium-F32.gguf","size":3057437088,"quant":"F32","sha256":"d716aa436e8d1d3164898d1fd6f4bde0f7cbbb7059b8c276b18f78cbca2faf6b"},{"name":"whisper-medium-Q4_K_M.gguf","size":504102848,"quant":"Q4_K_M","sha256":"6c9cad9c41d1fa0fcc624898f7ee3485b66127627878081a5655c6f6f3ce20ab"},{"name":"whisper-medium-Q5_K_M.gguf","size":582746048,"quant":"Q5_K_M","sha256":"4e2a8904a866b3aa7ef70d7640ec6abc5f0a05524cd950ea4b66ace12122bf53"},{"name":"whisper-medium-Q6_K.gguf","size":648019904,"quant":"Q6_K","sha256":"8718bafef4f595b5cacd9d9409fb7e19ce99b1afe4c6a450198d692fa58bd380"},{"name":"whisper-medium-Q8_0.gguf","size":831538144,"quant":"Q8_0","sha256":"09e6a65e7de377aa5b10bae24608bc6f8ca2ed04b3993ef10d4a02bcd9a82adf"}],"totalBytes":7165775456,"suggestedFile":"whisper-medium-Q4_K_M.gguf","requirements":{"ramGb":2,"diskBytes":504102848,"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-medium-gguf"}}