CoolFace
Modelpublic

cstr/moonshine-base-ar-GGUF

sourceHugging Faceotherupdated 2mo agoView on Hugging Face
0likes13downloads
Model Card

Moonshine Base (Arabic) -- GGUF

GGUF conversions and quantisations of `UsefulSensors/moonshine-base-ar` for use with [CrispStrobe/CrispASR](https://github.com/CrispStrobe/CrispASR).

Available variants

FileQuantSizeNotes
moonshine-base-ar.ggufF32235 MBFull precision
moonshine-base-ar-q4_k.ggufQ4_K40 MBBest size/quality tradeoff

Model details

  • —Architecture: Conv1d stem + 8L transformer encoder + 8L transformer decoder (416d, 8 heads, partial RoPE, SiLU/GELU)
  • —Parameters: 61M
  • —Languages: Arabic (fine-tuned from English moonshine-base)
  • —License: Moonshine AI Community License (free for <$1M revenue, attribution required)
  • —Source: `UsefulSensors/moonshine-base-ar`

Usage with CrispASR

bash
# Auto-download (English tiny only)
./build/bin/crispasr --backend moonshine -m auto -f audio.wav

# Explicit model path
./build/bin/crispasr --backend moonshine -m moonshine-base-ar-q4_k.gguf -f audio.wav

Notes

  • —Moonshine models run on CPU only (GPU not needed for these small models)
  • —Tokenizer (tokenizer.bin) must be in the same directory as the model file
  • —Base models use headdim=52 which works on CPU flashattn

Provenance and EU AI Act Art. 53 note

  • —Upstream model: UsefulSensors/moonshine-base-ar — published by UsefulSensors.
  • —Upstream licence: other. This repository redistributes under the same terms; it grants no rights the upstream licence does not.
  • —What was done here: format conversion and/or quantisation only (GGUF/GGML). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs.
  • —Training data: documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository.
  • —Provider status: under Regulation (EU) 2024/1689 the upstream authors remain the provider of this model. Converting the serialisation format does not make this repository the provider of a new general-purpose AI model, and no such claim is made. Questions about training content, copyright policy or model capability belong upstream.