apac_5sents_QoLT_largev2_freeze

This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0633
• Wer: 13.1696

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 600
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0111	5.54	100	0.0976	15.625
0.0002	11.11	200	0.1081	26.3393
0.0001	16.65	300	0.1100	35.2679
0.0001	22.22	400	0.1118	37.5
0.0001	27.76	500	0.1127	39.2857
0.0001	33.32	600	0.1130	39.7321

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.11.0
• Tokenizers 0.13.3