xbilek25/whisper-small-train-one_en_word-p3

Whisper small on xbilek25/cv11_csen_train_one_en_word_p3, save, eval: 100, max:300

This model is a fine-tuned version of openai/whisper-small on the xbilek25/cv11_csen_train_one_en_word_p3 dataset. It achieves the following results on the evaluation set:

• Loss: 0.7289
• Wer: 45.3422

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: 8
• 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: 300
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3061	3.01	100	0.6871	54.8701
0.0364	6.03	200	0.7091	46.4354
0.0091	9.04	300	0.7289	45.3422

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2