whisper-large-v2

This model is a fine-tuned version of openai/whisper-large-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6939
• Wer: 61.3949

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: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.7339	0.4548	1000	0.7139	92.6315
0.6643	0.9095	2000	0.6473	70.6068
0.4635	1.3643	3000	0.6340	62.1222
0.483	1.8190	4000	0.6160	61.5056
0.3238	2.2738	5000	0.6323	58.7863
0.3218	2.7285	6000	0.6318	61.8882
0.2262	3.1833	7000	0.6885	59.5842
0.1939	3.6380	8000	0.6939	61.3949

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu118
• Datasets 3.0.0
• Tokenizers 0.19.1