apac_5sents_QoLT_largev2_FT

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: 0.0866
• Wer: 71.6518

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
0.0062	5.54	100	0.0716	70.0893
0.0002	11.11	200	0.0915	71.6518
0.0001	16.65	300	0.0850	71.6518
0.0001	22.22	400	0.0859	71.6518
0.0001	27.76	500	0.0864	71.6518
0.0001	33.32	600	0.0866	71.6518

Framework versions

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