whisper-large-v3-finetuned-2

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

• Loss: 1.8292
• Wer: 29.2595

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-09
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.0224	1.0	7532	1.8944	30.6810
2.932	2.0	15064	1.8575	30.1652
1.6702	3.0	22596	1.8380	29.3775
1.9191	4.0	30128	1.8304	29.2800
2.155	5.0	37660	1.8292	29.2595

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2