whisper-small-kcn

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

• Loss: 0.0001
• Wer: 0.0

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: 0.0004
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 132
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.169	3.6364	100	0.2063	96.1615
0.1821	7.2727	200	0.1751	15.7029
0.0916	10.9091	300	0.0752	7.3779
0.052	14.5455	400	0.0588	7.0289
0.0327	18.1818	500	0.0372	6.0818
0.0092	21.8182	600	0.0004	0.5484
0.0011	25.4545	700	0.0001	0.0
0.0001	29.0909	800	0.0001	0.0

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1