abghany/cohere-transcribe-arabic-openvino-int8

automatic-speech-recognition model by abghany

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

OpenVINO port of CohereLabs/cohere-transcribe-arabic-07-2026, a 2 billion parameter Arabic speech recognition model, packaged to run fully on an Intel NPU. Tested on Core Ultra 7 255H (Arrow Lake) with intel level zero NPU driver 1.33 and OpenVINO 2026.4. Contents File sizes are roughly: encoder 3.8 GB in FP16 and 1.9 GB in INT8, cache less decoder 307 MB and 154 MB, KV step decoder 271 MB and 136 MB, cross K/V precompute 36 MB and 18 MB. Accuracy On 150 FLEURS Arabic clips, 27.7 minutes of audio, the INT8 KV cache pipeline on NPU scores 9.03 percent WER against 8.96 percent for the original model on GPU. The paired difference is plus 0.07 points with a 95 percent interval from minus 0.10 to plus 0.24. 96 percent of transcripts are identical. Full numbers with per clip references and hypotheses are in benchmarks/werpaired150.json, and the raw Kaggle baseline output is in…

abghany/cohere-transcribe-arabic-openvino-int8 on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-09-30T06:56:20.130Z

Inside the original model card — Document outline

Cohere Transcribe Arabic for Intel NPU

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

abghany/cohere-transcribe-arabic-openvino-int8 is a automatic-speech-recognition model repository published by abghany on Hugging Face. The source reports the openvino library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: automatic-speech-recognition
Library: openvino
Recent downloads (30 days): 0
Cumulative likes: 0
Hugging Face trending score: 0
Reported safetensors parameters: Not reported
Architecture: Not reported
License: apache-2.0
Access: Not gated by Hugging Face
Created: 2026-09-30T06:13:37.000Z
Last modified: 2026-09-30T06:27:48.000Z

Compatibility and lineage

Reported languages: ar, en

Reported base models: CohereLabs/cohere-transcribe-arabic-07-2026

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion