classla
/

wav2vecbert2-prosodicUnit

audio-frame-classification

Model card Files Files and versions

5roop commited on Oct 1

Commit

5df38ac

·

verified ·

1 Parent(s): fefb572

Update README.md

Files changed (1) hide show

README.md +1 -3

README.md CHANGED Viewed

@@ -302,10 +302,8 @@ print(final_intervals)
 | hyperparameter              | value |
 | --------------------------- | ----- |
 | learning rate               | 3e-5  |
-| batch size                  | 1     |
-| gradient accumulation steps | 16    |
 | num train epochs            | 20    |
-| weight decay                | 0.01  |
 Software environment can be found in mamba/conda [environment export yml
 file](transformers_env.yml). To recreate the environment with conda/mamba, run

 | hyperparameter              | value |
 | --------------------------- | ----- |
 | learning rate               | 3e-5  |
+| effective batch size        | 16    |
 | num train epochs            | 20    |
 Software environment can be found in mamba/conda [environment export yml
 file](transformers_env.yml). To recreate the environment with conda/mamba, run