Edit model card

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/basic_train_set_en_last3cs_1000 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3732
  • Wer: 29.7470

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: 200
  • training_steps: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0021 7.03 500 0.3407 32.9174
0.0008 15.03 1000 0.3548 27.6897
0.0005 23.03 1500 0.3684 30.3204
0.0004 31.02 2000 0.3732 29.7470

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.15.2
Downloads last month
2
Safetensors
Model size
242M params
Tensor type
F32
·

Finetuned from

Dataset used to train xbilek25/whisper-small-train-v2.0

Evaluation results

  • Wer on xbilek25/basic_train_set_en_last3cs_1000
    self-reported
    29.747