hc-train-v3-independent-v2

This model is a fine-tuned version of openai/whisper-large-v3 on the honzapucalek/hc_train_v3_independent_v2 cs dataset. It achieves the following results on the evaluation set:

• Loss: 0.3728
• Wer: 0.1169

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
0.0079	13.51	1000	0.2854	0.1256
0.0037	27.03	2000	0.3198	0.1373
0.0002	40.54	3000	0.3459	0.1177
0.0001	54.05	4000	0.3650	0.1168
0.0001	67.57	5000	0.3728	0.1169

Framework versions

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