Skip to content

Commit

Permalink
Dataset diff
Browse files Browse the repository at this point in the history
  • Loading branch information
@MiscellaneousStuff
MiscellaneousStuff committed Aug 31, 2022
1 parent 30ebad5 commit 358b66c
Showing 1 changed file with 6 additions and 0 deletions.
6 changes: 6 additions & 0 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,12 @@ this process with the current SOTA transduction model, you would have to use
the vocoder inbetween the transduction model and the deepspeech-0.7.0 model
used for the evaluations.

## Performance

The speech recognition trained uses 115 times less training data than using
the evaluation function in the original "An Improved Model for Voicing Silent Speech"
at ACL 2021 paper.

## Data

The dataset for this project is based on the open-source dataset released
Expand Down

0 comments on commit 358b66c

Please sign in to comment.