whisper small: transcribe.cpp GGUF GGUF conversions of openai/whisper small for use with transcribe.cpp. Ported from upstream commit 973afd2, pinned 2026 04 25. Validated against the transformers reference at transcribe.cpp commit 5.6.1 on 2026 04 26. OpenAI 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. Downloads Quantization Download Size WER (LibriSpeech test clean) : : F32 whisper small F32.gguf 924 MB 3.33% F16 whisper small F16.gguf 470 MB 3.34% Q8 0 whisper small Q8 0.gguf 257 MB 3.33% Q6 K whisper small Q6 K.gguf 202 MB 3.33% Q5 K M whisper small Q5 K M.gguf 185 MB 3.37% Q4 K M whisper small Q4 K M.gguf 164 MB 3.40% 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 3.432%. We don't know upstream's exact eval config, but the most likely cause of any divergence is that OpenAI's model.ge…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy