granite speech 4.1 2b nar: transcribe.cpp GGUF GGUF conversions of ibm granite/granite speech 4.1 2b nar for use with transcribe.cpp. Ported from upstream commit 99a4df9, pinned 2026 05 24. Validated against the Transformers reference at transcribe.cpp commit c53af2c on 2026 05 24. Offline multilingual speech to text in a single non autoregressive editor pass. IBM Granite Speech 4.1 2b NAR shares the Conformer audio encoder with the AR Granite Speech family but pairs it with a custom MLP with attention projector and the Granite 4.0 1b LLM used as a bidirectional editor (causal mask disabled). One forward pass produces logits over the full transcript; CTC decode yields the final text. No token by token loop. Takes a 16 kHz mono WAV and produces a transcript. English plus French, German, Spanish, and Portuguese; ASR only (no translation, no timestamps). Downloads Quantization Download Size WER (LibriSpeech test clean) : : BF16 granite speech 4.1 2b nar BF16.gguf 4.20 GB 1.29% F16 granite speech 4.1 2b nar F16.gguf 4.21 GB 1.29% Q8 0 granite speech 4.1 2b nar Q8 0.gguf 2.33 GB 1.29% Q6 K granite speech 4.1 2b nar Q6 K.gguf 1.84 GB 1.29% Q5 K M granite speech 4.1 2b nar Q5 K M.gguf 1.6…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy