xbilek25/whisper-small-train-v3.3

basic_train_basic_test 1000 similar params: per_device_train_batch_size=32, # bylo 16 a pod tim 1 gradient_accumulation_steps=2, warmup_steps=300, max_steps=3000

This model is a fine-tuned version of openai/whisper-small on the xbilek25/train_set_1sd_1000_en_de_en_v2.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5619
• Wer: 21.9295

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: 800
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0038	6.03	400	0.5352	26.8218
0.0018	12.05	800	0.5619	21.9295

Framework versions

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