parakeet ctc 1.1b: transcribe.cpp GGUF GGUF conversions of nvidia/parakeet ctc 1.1b for use with transcribe.cpp. Ported from upstream commit a707e81, pinned 2026 05 10. Validated against the NeMo reference at transcribe.cpp commit 42528dd on 2026 05 10. Offline English speech to text with greedy CTC decoding. A 1.1B parameter FastConformer XL encoder with a linear CTC head. Output is lowercase, no punctuation. Not a streaming model and does not translate. Downloads Quantization Download Size WER (LibriSpeech test clean) : : F32 parakeet ctc 1.1b F32.gguf 4.25 GB 1.85% F16 parakeet ctc 1.1b F16.gguf 2.13 GB 1.85% Q8 0 parakeet ctc 1.1b Q8 0.gguf 1.26 GB 1.85% Q6 K parakeet ctc 1.1b Q6 K.gguf 1.04 GB 1.85% Q5 K M parakeet ctc 1.1b Q5 K M.gguf 929 MB 1.84% Q4 K M parakeet ctc 1.1b Q4 K M.gguf 818 MB 1.90% WER measured on the full LibriSpeech test clean split (2620 utterances) with greedy CTC decoding and no external LM. F32 reference baseline: 1.85%. NVIDIA's self reported number on the same split is 1.83%. Usage Build transcribe.cpp from source: Run on a 16 kHz mono WAV: If your audio isn't already 16 kHz mono WAV, convert it first: See the transcribe.cpp model page for performance n…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy