whisperfinetune_modelcheckpointsv2

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1296
• Wer: 17.1313

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0583	1.63	1000	0.1125	10.2794
0.0113	3.26	2000	0.1196	15.8164
0.0049	4.89	3000	0.1249	17.3557
0.0011	6.53	4000	0.1296	17.1313

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0