whisper-baset

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

• Loss: 0.0001
• Wer: 1.9802

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: 16
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	100.0	100	0.0009	1.9802
No log	200.0	200	0.0003	1.9802
No log	300.0	300	0.0002	1.9802
No log	400.0	400	0.0001	1.9802
0.0555	500.0	500	0.0001	1.9802
0.0555	600.0	600	0.0001	1.9802
0.0555	700.0	700	0.0001	1.9802
0.0555	800.0	800	0.0001	1.9802
0.0555	900.0	900	0.0001	1.9802
0.0001	1000.0	1000	0.0001	1.9802

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1