Modelpublic

Fazmin/solus_v1_parakeet-tdt-0.6b-v3-q8

sourceHugging Facecc-by-4.0updated 2mo agoView on Hugging Face

0likes9downloads

Model Card

Parakeet TDT 0.6B v3 (Q8_0) — Solus v1

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.

Specifications


Parameters	0.6B
Quantization	Q8_0
File size	705.25 MB
Minimum RAM	2.00 GB
Minimum VRAM	not required
Context length	n/a (audio model)
SHA-256	`5859f77944efcd8eafa23a6350731960b2b55b2203df51f319665c807d802cc7`

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

Quantization

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.

Provenance

—Original model: nvidia/parakeet-tdt-0.6b-v3
—Upstream GGUF: handy-computer/parakeet-tdt-0.6b-v3-gguf
—Mirrored for Solus, a desktop app for running language models entirely on your own machine.

Usage

bash

transcribe-cli -m parakeet-tdt-0.6b-v3-Q8_0.gguf audio.wav

Expects 16 kHz mono audio.

License

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