whisper base: transcribe.cpp GGUF GGUF conversions of openai/whisper base for use with transcribe.cpp. Ported from upstream commit e37978b, pinned 2026 04 25. Validated against the transformers reference at transcribe.cpp commit 5.6.1 on 2026 04 26. OpenAI Whisper base — 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 base F32.gguf 279 MB 5.10% F16 whisper base F16.gguf 144 MB 5.10% Q8 0 whisper base Q8 0.gguf 81 MB 5.12% Q6 K whisper base Q6 K.gguf 65 MB 5.12% Q5 K M whisper base Q5 K M.gguf 61 MB 5.19% Q4 K M whisper base Q4 K M.gguf 56 MB 5.36% 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 5.009%. We don't know upstream's exact eval config, but the most likely cause of any divergence is that OpenAI's model.generate() defa…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy