cohere transcribe 03 2026: transcribe.cpp GGUF GGUF conversions of CohereLabs/cohere transcribe 03 2026 for use with transcribe.cpp. Ported from upstream commit 76b8b23, pinned 2026 04 16. Validated against the Transformers reference at transcribe.cpp commit bf0d0b7 on 2026 04 18. Offline multilingual speech to text covering 14 languages (English, French, German, Spanish, Italian, Portuguese, Dutch, Polish, Greek, Arabic, Japanese, Chinese, Vietnamese, Korean). A Conformer encoder with a Transformer encoder decoder head (cross attention, tied token embedding). Takes a 16 kHz mono WAV and produces a transcript. Decoding is autoregressive. Downloads Quantization Download Size WER (LibriSpeech test clean) : : BF16 cohere transcribe 03 2026 BF16.gguf 4.10 GB 1.26% F16 cohere transcribe 03 2026 F16.gguf 4.11 GB 1.26% Q8 0 cohere transcribe 03 2026 Q8 0.gguf 2.41 GB 1.27% Q6 K cohere transcribe 03 2026 Q6 K.gguf 1.97 GB 1.27% Q5 K M cohere transcribe 03 2026 Q5 K M.gguf 1.76 GB 1.25% Q4 K M cohere transcribe 03 2026 Q4 K M.gguf 1.55 GB 1.25% WER measured on the full LibriSpeech test clean split (2620 utterances) with greedy decoding and no external LM. BF16 reference baseline: 1.26%. Coh…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy