whispy
/

whisper_hf

Automatic Speech Recognition

hf-asr-leaderboard

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

whispy commited on Dec 8, 2022

Commit

5a85972

·

1 Parent(s): 021e317

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -51,14 +51,14 @@ The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 16
 - eval_batch_size: 8
-<!-- - seed: 42 -->
 - gradient_accumulation_steps: 1
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
 - training_steps: 954
-<!-- - mixed_precision_training: Native AMP -->
 ### Training results

 - learning_rate: 1e-05
 - train_batch_size: 16
 - eval_batch_size: 8
+- seed: 42
 - gradient_accumulation_steps: 1
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
 - training_steps: 954
+- mixed_precision_training: Native AMP
 ### Training results