README.md

metadata

language:
  - en
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - Jzuluaga/atcosim_corpus
metrics:
  - wer
model-index:
  - name: Whisper Small En - Whisper with ATCOSIM
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Air Traffic Control Simulation Speech corpus
          type: Jzuluaga/atcosim_corpus
          args: 'config: en, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 1.4442187085946472

Whisper Small En - Whisper with ATCOSIM

This model is a fine-tuned version of openai/whisper-small on the Air Traffic Control Simulation Speech corpus dataset. It achieves the following results on the evaluation set:

• Loss: 0.0487
• Wer: 1.4442

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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0014	2.09	1000	0.0482	1.5944
0.0001	4.18	2000	0.0491	1.5944
0.0	6.28	3000	0.0480	1.4266
0.0	8.37	4000	0.0487	1.4442

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2