README.md

metadata

language: aii
license: cc0-1.0
tags:
  - audio
  - automatic-speech-recognition
  - speech
datasets:
  - mnazari/urmi-assyrian-voice
metrics:
  - cer
model-index:
  - name: Wav2Vec2-Assyrian by Matthew Nazari
    results:
      - task:
          type: automatic-speech-recognition
          name: Speech Recognition
        dataset:
          type: mnazari/urmi-assyrian-voice
          name: Urmi Assyrian Voice
        metrics:
          - type: cer
            value: 7.5
            name: Train CER
          - type: cer
            value: 12.071
            name: Test CER

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.