output_dir

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9972
• Wer: 99.4455

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: 2
• eval_batch_size: 2
• seed: 42
• 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
1.9297	1.0152	1000	1.9972	99.4455
1.1678	2.0305	2000	1.9989	99.4455
0.5123	3.0457	3000	2.0867	102.4030
0.2025	4.0609	4000	2.1698	103.3272
0.0843	5.0761	5000	2.2214	104.2514

Framework versions

• Transformers 4.44.1
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1