Moonshine Base Ar GGUF

--- license: other license_name: moonshine-ai-community language: - ar pipeline_tag: automatic-speech-recognition tags: - audio - speech-recognition - transcription - gguf - moonshine - lightweight library_name: ggml base_model: UsefulSensors/moonshine-base-ar --- # Moonshine Base (Arabic) -- GGUF GGUF conversions and quantisations of [`UsefulSensors/moonshine-base-ar`](https://huggingface.co/UsefulSensors/moonshine-base-ar) for use with **[CrispStrobe/CrispASR](https://github.com/CrispStrobe/CrispASR)**. ## Available variants | File | Quant | Size | Notes | |---|---|---|---| | `moonshine-base-ar.gguf` | F32 | 235 MB | Full precision | | `moonshine-base-ar-q4_k.gguf` | Q4_K | 40 MB | Best 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](https://huggingface.co/UsefulSensors/moonshine-tiny-ja/blob/main/LICENSE.txt) (free for <$1M revenue, attribution required) - **Source:** [`UsefulSensors/moonshine-base-ar`](https://huggingface.co/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 head_dim=52 which works on CPU flash_attn ## Provenance and EU AI Act Art. 53 note - **Upstream model:** [UsefulSensors/moonshine-base-ar](https://huggingface.co/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 c...

--- license: other license_name: moonshine-ai-community language: - ar pipeline_tag: automatic-speech-recognition tags: - audio - speech-recognition - transcription - gguf - moonshine - lightweight library_name: ggml base_model: UsefulSensors/moonshine-base-ar --- # Moonshine Base (Arabic) -- GGUF GGUF conversions and quantisations of [`UsefulSensors/moonshine-base-ar`](https://huggingface.co/UsefulSensors/moonshine-base-ar) for use with **[CrispStrobe/CrispASR](https://github.com/CrispStrobe/CrispASR)**. ## Available variants | File | Quant | Size | Notes | |---|---|---|---| | `moonshine-base-ar.gguf` | F32 | 235 MB | Full precision | | `moonshine-base-ar-q4_k.gguf` | Q4_K | 40 MB | Best 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](https://huggingface.co/UsefulSensors/moonshine-tiny-ja/blob/main/LICENSE.txt) (free for <$1M revenue, attribution required) - **Source:** [`UsefulSensors/moonshine-base-ar`](https://huggingface.co/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 head_dim=52 which works on CPU flash_attn

Source context: 24 downloads · 0 likes · Pipeline automatic-speech-recognition · Library ggml · Repo cstr/moonshine-base-ar-GGUF