xbilek25/whisper-small-train-v3.1

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: 0.6814
• Wer: 22.2374

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: 500
• training_steps: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0044	9.01	600	0.5872	21.2453
0.0007	19.0	1200	0.6347	21.4848
0.0004	28.01	1800	0.6607	21.9295
0.0003	38.0	2400	0.6757	22.1348
0.0003	47.01	3000	0.6814	22.2374

Framework versions

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