mnazari
/

wav2vec2-assyrian

Automatic Speech Recognition Transformers PyTorch

Assyrian Neo-Aramaic wav2vec2 audio speech Eval Results Inference Endpoints

Model card Files Files and versions Community

Edit model card

Wav2Vec2-Assyrian

Fine-tuned facebom3hrdadfiok/wav2vec2-large-xlsr-persian-v3 in Assyrian (the Urmi dialect of North-Eastern Neo-Aramaic) using Urmi Assyrian Voice.

Please reach out to me at matthewnazari@college.harvard.edu if you are Assyrian or a researcher.

Downloads last month: 5

Dataset used to train mnazari/wav2vec2-assyrian

Evaluation results

Train CER on Urmi Assyrian Voice
self-reported

7.500
Test CER on Urmi Assyrian Voice
self-reported

12.071

View on Papers With Code