README.md

metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - lozgen
metrics:
  - wer
model-index:
  - name: whisper-medium-lozgen-male-model
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: lozgen
          type: lozgen
        metrics:
          - name: Wer
            type: wer
            value: 0.4796960341961529

whisper-medium-lozgen-male-model

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

• Loss: 0.7984
• Wer: 0.4797

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• 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
1.2961	2.9851	200	0.7984	0.4797
0.2221	5.9701	400	0.8183	0.4540
0.0963	8.9552	600	0.8391	0.3890
0.0457	11.9403	800	0.8436	0.3887

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0