---

license: apache-2.0

language:

• en
• multilingual

tags:

• speech
• asr
• gguf
• ggml
• omniasr

pipeline_tag: automatic-speech-recognition

base_model: aadel4/omniASR-CTC-300M-v2

---

OmniASR CTC-300M-v2 — GGUF

GGUF conversion of aadel4/omniASR-CTC-300M-v2 for use with CrispASR.

OmniASR is Meta's multilingual ASR model family supporting 1600+ languages. Apache-2.0 license.

Works on audio ≤5 seconds (model positional encoding limit). Use --vad for longer audio.

Files

| File | Size |

| --- | ---: |

| omniasr-ctc-300m-v2-q4_k.gguf | 194 MB |

| omniasr-ctc-300m-v2-q8_0.gguf | 343 MB |

| omniasr-ctc-300m-v2.gguf | 623 MB |

Quick Start

git clone https://github.com/CrispStrobe/CrispASR && cd CrispASR
cmake -B build -DCMAKE_BUILD_TYPE=Release && cmake --build build -j$(nproc)

./build/bin/crispasr --backend omniasr -m auto --auto-download -f audio.wav

Conversion

Converted using CrispASR's converter scripts with fixed positional conv weight normalization (per-kernel-position norm, not per-output-channel).

Provenance and EU AI Act Art. 53 note

• Upstream model: aadel4/omniASR-CTC-300M-v2 — published by aadel4.
• Upstream licence: apache-2.0. 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. No training-content summary was found on the upstream model card at the time of writing; that documentation gap is upstream's and is not filled here.
• 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.