Mutqin Asr

--- license: apache-2.0 base_model: - tarteel-ai/whisper-base-ar-quran tags: - automatic-speech-recognition - quran - sherpa-onnx - onnx --- # Mutqin ASR — sherpa-onnx export of Tarteel's Qur'an Whisper models ONNX (int8) exports of [Tarteel AI](https://huggingface.co/tarteel-ai)'s Qur'an-fine-tuned Whisper checkpoints, in the layout [sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx) expects, for on-device recitation checking in the Mutqin app. Converted with `tools/asr/convert.py`. ## Attribution and licence The models are derived from Tarteel AI's checkpoints, licensed **Apache-2.0**: - `tarteel-ai/whisper-tiny-ar-quran` - `tarteel-ai/whisper-base-ar-quran` These exports are redistributed under the same Apache-2.0 licence. Weights are unchanged — only remapped to the openai-whisper layout, exported to ONNX and dynamically quantized to int8. All credit for the fine-tuning is Tarteel's. ## Layout models/quran-tiny/{encoder.int8.onnx,decoder.int8.onnx,tokens.txt} # ~99 MB models/quran-base/{encoder.int8.onnx,decoder.int8.onnx,tokens.txt} # ~153 MB The decoder dominates: sherpa's export quantizes `MatMul` only, so the 51865-row token embedding stays float32. Quantizing `Gather` too makes it *larger* — Whisper reuses that embedding for the output projection, so an int8 copy is added rather than substituted. ## Accuracy WER reported by Tarteel on clean audio: 7.05% (tiny), 5.75% (base). Not independently verified here, and int8 quantization is not free — measure on your own audio before trusting it.

Source context: 0 downloads · 0 likes · Pipeline automatic-speech-recognition · Repo rifartboy/mutqin-asr