xbilek25/w-medium-lang_en-set-en-de-en_similar

TMP prvontni trenovani jazyk en, train en de en similar

This model is a fine-tuned version of openai/whisper-medium on the xbilek25/train_set_1st_1000_de_en_de dataset. It achieves the following results on the evaluation set:

• Loss: 0.3401
• Wer: 17.3873

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: 1
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0979	1.12	500	0.2481	19.0875
0.0097	3.12	1000	0.2917	16.7763
0.0017	5.12	1500	0.3298	16.9689
0.0011	7.12	2000	0.3401	17.3873

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.15.2