README.md

metadata

datasets:
  - SLPRL-HUJI/HebDB
language:
  - he
metrics:
  - wer
  - cer
pipeline_tag: text-to-speech

Details

This model is an implementation of the vall-e architecture, with the AlephBert text tokenizer. This model was trained as a final project in the "DSP & audio processing using Deep Learning" class at Tel-Aviv University, Israel.

Implementation details and references can be found in the included 'paper' PDF.