parakeet rnnt 1.1b: transcribe.cpp GGUF GGUF conversions of nvidia/parakeet rnnt 1.1b for use with transcribe.cpp. Ported from upstream commit a07b19e, 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 RNN T decoding. A 1.1B parameter FastConformer XL encoder with an RNN T transducer decoder. Output is lowercase, no punctuation. Not a streaming model and does not translate. Downloads Quantization Download Size WER (LibriSpeech test clean) : : F32 parakeet rnnt 1.1b F32.gguf 4.28 GB 1.45% F16 parakeet rnnt 1.1b F16.gguf 2.15 GB 1.45% Q8 0 parakeet rnnt 1.1b Q8 0.gguf 1.27 GB 1.46% Q6 K parakeet rnnt 1.1b Q6 K.gguf 1.04 GB 1.43% Q5 K M parakeet rnnt 1.1b Q5 K M.gguf 936 MB 1.43% Q4 K M parakeet rnnt 1.1b Q4 K M.gguf 825 MB 1.41% WER measured on the full LibriSpeech test clean split (2620 utterances) with greedy RNN T decoding and no external LM. F32 reference baseline: 1.45%. NVIDIA's self reported number on the same split is 1.46%. 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…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy