diactc-wav2vec2-clartts – AI Model by rufaelfekadu | AlphaNeural AI

You can deploy this model and start earning money today!

rufaelfekadu/
diactc-wav2vec2-clartts

like

0

automatic-speech-recognition

jonatasgrosman/wav2vec2-large-xlsr-53-arabic

Views

No views yet

DiaCTC — Wav2Vec2 (ClArTTS)

Fine-tuned Wav2Vec2 CTC model for Arabic diacritic restoration from speech + undiacritized transcript, trained on ClArTTS (Classical Arabic).

This checkpoint is used with DiaCTC constrained WFST decoding. Try the interactive demo: DiaCTC Space.

Results (ClArTTS training)

Test set	WER ↓	DER ↓
ClArTTS	11.21	3.53
ArVoice	39.89	12.04

Base encoder: jonatasgrosman/wav2vec2-large-xlsr-53-arabic.

Usage

python

from diactc.models import Wav2Vec2DiacritizationModel

model = Wav2Vec2DiacritizationModel(
    "rufaelfekadu/diactc-wav2vec2-clartts",
    device="cuda",
    use_blank_token=True,
    use_no_diac_token=True,
    use_unk_diac_token=True,
)
text, rtf = model.diacritize(
    undiacritized_text,
    audio_path,
    constrained=True,
    method="wfst",
)

Citation

bibtex

@article{marew2026constrained,
  title   = {Constrained CTC Decoding for Efficient Diacritic Restoration},
  author  = {Marew, Rufael and Keleg, Amr and Aldarmaki, Hanan},
  journal = {arXiv preprint arXiv:TBD},
  year    = {2026}
}