metadata

license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - generated_from_trainer
datasets:
  - honzapucalek/p6_severe
metrics:
  - wer
model-index:
  - name: p6_severe
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: honzapucalek/p6_severe cs
          type: honzapucalek/p6_severe
          config: cs
          split: test
          args: cs
        metrics:
          - name: Wer
            type: wer
            value: 0.4488029997115662

p6_severe

This model is a fine-tuned version of openai/whisper-large-v3 on the honzapucalek/p6_severe cs dataset. It achieves the following results on the evaluation set:

Loss: 1.7055
Wer: 0.4488

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0001	95.24	1000	1.5192	0.4586
0.0	190.48	2000	1.6149	0.4479
0.0	285.71	3000	1.6635	0.4505
0.0	380.95	4000	1.6947	0.4485
0.0	476.19	5000	1.7055	0.4488

Framework versions

Transformers 4.37.2
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.1