whisper-bs-cs-train-aug-test-aug2

This model is a fine-tuned version of openai/whisper-base on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6875
• Wer: 54.1533

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6476	1.4440	1000	0.8181	63.1377
0.4531	2.8881	2000	0.7081	56.8700
0.3048	4.3321	3000	0.6906	54.5125
0.2841	5.7762	4000	0.6875	54.1533

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1