hc-impaired-all-v3

This model is a fine-tuned version of openai/whisper-large-v3 on the honzapucalek/hc_impaired_all_v3 cs dataset. It achieves the following results on the evaluation set:

• Loss: 0.3837
• Wer: 0.1107

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• 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: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0275	6.87	1000	0.2212	0.1163
0.0021	13.75	2000	0.3051	0.1123
0.0004	20.62	3000	0.3517	0.1113
0.0001	27.49	4000	0.3760	0.1104
0.0001	34.36	5000	0.3837	0.1107

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1