Update README.md
Browse files
README.md
CHANGED
|
@@ -29,4 +29,4 @@ pipeline_tag: automatic-speech-recognition
|
|
| 29 |
|
| 30 |
This architecture introduces parallel downsampling layers before the first and last exits to improve performance with minimal extra overhead, while retaining inference speed.
|
| 31 |
|
| 32 |
-
Our code is available on our [GitHub](https://github.com/augustgw/early-exit-transformer) repository.
|
|
|
|
| 29 |
|
| 30 |
This architecture introduces parallel downsampling layers before the first and last exits to improve performance with minimal extra overhead, while retaining inference speed.
|
| 31 |
|
| 32 |
+
Our code for training and inference is available on our [GitHub](https://github.com/augustgw/early-exit-transformer) repository.
|