NbAiLabArchive
/

whisper-large-v2-nob

Automatic Speech Recognition

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

pere commited on Dec 16, 2022

Commit

1302198

•

1 Parent(s): 7b1c102

readme

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -55,8 +55,8 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant with warmpu
-- lr_scheduler_warmup_steps: 100
-- training_steps: 10.000 (currently 1.000)
 - mixed_precision_training: fp16
 - deepspee: true

 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant with warmpu
+- lr_scheduler_warmup_steps: 1000
+- training_steps: 50.000 (currently @1.000)
 - mixed_precision_training: fp16
 - deepspee: true