13123

This model is a fine-tuned version of openai/whisper-base on the arrow dataset. It achieves the following results on the evaluation set:

• Loss: 0.4595
• Cer: 16.7167

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: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.01
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.5184	0.1290	1000	0.5136	17.8441
0.4716	0.2581	2000	0.4829	17.0947
0.4664	0.3871	3000	0.4666	16.9219
0.4575	0.5161	4000	0.4595	16.7167

Framework versions

• Transformers 4.41.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1