whisper large v3 turbo: transcribe.cpp GGUF GGUF conversions of openai/whisper large v3 turbo for use with transcribe.cpp. Ported from upstream commit 41f01f3, pinned 2026 04 25. Validated against the transformers reference at transcribe.cpp commit 5.6.1 on 2026 04 26. OpenAI Whisper large v3 turbo — converted to GGUF for transcribe.cpp. Multilingual transcription and language detection across 100 languages. Transcription only: unlike the rest of the multilingual family, turbo was fine tuned on transcription data with translation excluded, so task="translate" is not supported (use whisper large v3 for speech translation). v3 family adds Cantonese (yue) and uses a 128 bin mel input. Encoder decoder transformer; 30 second windows with chunked long form decoding. Downloads Quantization Download Size WER (LibriSpeech test clean) : : F16 whisper large v3 turbo F16.gguf 1.51 GB 2.00% Q8 0 whisper large v3 turbo Q8 0.gguf 845 MB 2.00% Q6 K whisper large v3 turbo Q6 K.gguf 660 MB 1.96% Q5 K M whisper large v3 turbo Q5 K M.gguf 591 MB 2.00% Q4 K M whisper large v3 turbo Q4 K M.gguf 511 MB 2.00% WER measured on the full LibriSpeech test clean split (2620 utterances) with the transcribe.cpp d…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy