Makkoen/whisper-large-v3-cit-do005-wd0-lr5e-06-steps1200-CA

CA

This model is a fine-tuned version of openai/whisper-large-v3 on the 3309 CA-2024-12-01 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4526
• Wer Ortho: 21.9410
• Wer: 15.1505

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: 5e-06
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 4
• 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: 300
• training_steps: 1200
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.6296	1.0738	200	0.4426	24.2755	17.3001
0.3923	2.1477	400	0.4143	22.7639	15.8469
0.2856	3.2215	600	0.4175	22.3166	15.5460
0.2101	4.2953	800	0.4351	22.1020	15.3224
0.1688	5.3691	1000	0.4375	21.9589	15.3740
0.1306	6.4430	1200	0.4526	21.9410	15.1505

Framework versions

• Transformers 4.44.0
• Pytorch 1.13.1+cu117
• Datasets 2.21.0
• Tokenizers 0.19.1