Modelpublic

OpenVoiceOS/whisper-large-v3-turbo-arabic-dialectal-v2-onnx

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

0likes

Model Card

whisper-large-v3-turbo-arabic-dialectal-v2 — ONNX

ONNX export of oddadmix/whisper-large-v3-turbo-arabic-dialectal-v2 (Whisper large-v3-turbo fine-tuned by oddadmix for dialectal Arabic, base model openai/whisper-large-v3-turbo) for onnx-asr (standard whisper model type — works with stock onnx-asr, no patches needed). fp32 and int8 (dynamic-quantized) variants included.

License: apache-2.0 (verbatim from the base model card).

Dialect coverage

Trained on oddadmix/lahgtna-v3-small (dialect-balanced, undiacritized targets). Per the source model card, evaluated across 13 Arabic dialects (Gulf/Saudi, Iraqi, Egyptian, Syrian, Bahraini, Yemeni, Palestinian, Lebanese, Libyan, Tunisian, Algerian, Moroccan, Sudanese). Gulf/Saudi is consistently the strongest dialect; Maghrebi dialects (esp. Tunisian) are the weakest across the whole oddadmix v2 family. This ONNX export does not change accuracy; it reproduces the source model's behavior.

Usage

python

import onnx_asr
model = onnx_asr.load_model("whisper", "path/to/this/repo")  # or quantization="int8"
print(model.recognize("audio_16khz.wav", language="ar"))

Verification

Verified against FLEURS ar_eg clips (fp32 and int8): both produce fluent, near-identical undiacritized Arabic transcriptions consistent with the source model's reported accuracy; noticeably higher fidelity than the whisper-small variant of this family (fewer word-substitution errors).

RTF (CPU, homelab box, shared load): fp32 ~0.7-1.2, int8 ~0.3-0.65.