whisper_checkpoints7

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

• Loss: 0.0170
• Wer: 20.9137

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: 24
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• 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
0.009	2.5510	1000	0.0306	21.4887
0.0011	5.1020	2000	0.0184	22.1210
0.0005	7.6531	3000	0.0172	21.3229
0.0004	10.2041	4000	0.0170	20.9137

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0