training

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

• Loss: 0.3025
• Wer: 24.5340

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
• 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
0.3282	0.81	1000	0.3106	42.8176
0.1619	1.62	2000	0.2932	27.0624
0.0531	2.43	3000	0.2985	25.3645
0.0208	3.24	4000	0.3025	24.5340

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.2.1+cu118
• Datasets 2.17.1
• Tokenizers 0.15.2