NVIDIA's Parakeet TDT 0.6B v3, converted to GGUF for transcribe.cpp. Offline speech-to-text across 25 European languages, using a 0.6B Conformer encoder with a TDT/RNNT transducer decoder. It takes 16 kHz mono audio and returns a transcript with optional token-level timestamps.

This is the Q8_0 build and the most accurate transcription model in the Solus catalogue, at 1.94% word error rate on LibriSpeech test-clean. Note that it does not stream and does not translate.

Single file: parakeet-tdt-0.6b-v3-Q8_0.gguf

Quantization performed at the Faculty of Engineering, McMaster University.

The GGUF conversion this build is derived from was produced by handy-computer, and the weights here are a byte-for-byte copy of that file — the SHA-256 above matches the upstream artifact.

Expects 16 kHz mono audio.

Licensed CC-BY-4.0. Attribution to NVIDIA is required when redistributing this model or its derivatives.