whisper-large-v2-ca-15awr

This model is a fine-tuned version of openai/whisper-large-v2 on the cymen-arfor/15awr train[:100%] main dataset. It achieves the following results on the evaluation set:

• Loss: 0.9218
• Wer: 0.3557

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: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.18	3.1201	1000	0.5585	0.3771
0.0328	6.2402	2000	0.6915	0.3700
0.0086	9.3604	3000	0.8111	0.3621
0.0017	12.4805	4000	0.8715	0.3603
0.0008	15.6006	5000	0.9218	0.3557

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1