Modelpublic

Fazmin/solus_v1_parakeet-tdt_ctc-110m-q8

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

0likes9downloads

Model Card

Parakeet TDT-CTC 110M (Q8_0) — Solus v1

The smallest and fastest transcription model in the Solus catalogue: NVIDIA's Parakeet TDT-CTC 110M, converted to GGUF for transcribe.cpp. English only.

At 110M parameters it runs comfortably on almost any laptop and is several times faster than the 0.6B models, for a modest accuracy cost: 2.43% word error rate on LibriSpeech test-clean. Does not stream and does not translate.

Specifications


Parameters	110M
Quantization	Q8_0
File size	129.10 MB
Minimum RAM	1.00 GB
Minimum VRAM	not required
Context length	n/a (audio model)
SHA-256	`7dd44c74a331d788a4e5f8b16913b3feb29ced22cf5613aad0e0f6cd30516296`

Single file: parakeet-tdt_ctc-110m-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_ctc-110m
—Upstream GGUF: handy-computer/parakeet-tdt_ctc-110m-gguf
—Mirrored for Solus, a desktop app for running language models entirely on your own machine.

Usage

bash

transcribe-cli -m parakeet-tdt_ctc-110m-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.