whisper medium: transcribe.cpp GGUF GGUF conversions of openai/whisper medium for use with transcribe.cpp. Ported from upstream commit abdf7c3, pinned 2026 04 25. Validated against the transformers reference at transcribe.cpp commit 5.6.1 on 2026 04 26. OpenAI 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. Downloads Quantization Download Size WER (LibriSpeech test clean) : : F32 whisper medium F32.gguf 2.85 GB 2.63% F16 whisper medium F16.gguf 1.44 GB 2.63% Q8 0 whisper medium Q8 0.gguf 793 MB 2.64% Q6 K whisper medium Q6 K.gguf 618 MB 2.59% Q5 K M whisper medium Q5 K M.gguf 556 MB 2.62% Q4 K M whisper medium Q4 K M.gguf 481 MB 2.59% WER measured on the full LibriSpeech test clean split (2620 utterances) with the transcribe.cpp default decode (greedy, suppress tokens, temperature fallback, segment timestamps enabled). OpenAI's self reported number on the same split is 2.90%. We don't know upstream's exact eval config, but the most likely cause of any divergence is that OpenAI'…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy