README.md

metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - BrainTheos/ojpl
metrics:
  - wer
model-index:
  - name: whisper-tiny-ln-ojpl-2
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: BrainTheos/ojpl
          type: BrainTheos/ojpl
          config: default
          split: train
          args: default
        metrics:
          - name: Wer
            type: wer
            value: 0.4351648351648352

whisper-tiny-ln-ojpl-2

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

• Loss: 1.2661
• Wer Ortho: 50.1855
• Wer: 0.4352

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.1767	11.36	500	0.9122	52.1142	0.4579
0.0191	22.73	1000	1.0786	53.7463	0.4538
0.0059	34.09	1500	1.1891	53.2641	0.4766
0.0019	45.45	2000	1.2661	50.1855	0.4352

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.0+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3