D4niel0s's picture
Update README.md
a66fdc5 verified
|
Raw
History Blame
289 Bytes
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. Implementation details and references can be found in the included 'paper' PDF.