whisper-large-v3-finetuned-1

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: 1.8569
• Wer: 29.2098

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
1.0462	1.0	7532	1.9223	30.9785
0.4373	2.0	15064	1.8852	30.1356
0.6992	3.0	22596	1.8657	29.4302
1.6049	4.0	30128	1.8581	29.2253
1.0439	5.0	37660	1.8569	29.2098

Framework versions

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