README.md

metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - yt
metrics:
  - wer
model-index:
  - name: Whisper Small Indonesian
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: yt id
          type: yt
        metrics:
          - name: Wer
            type: wer
            value: 76.37636988522145

Whisper Small Indonesian

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

• Loss: 1.1651
• Wer: 76.3764

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: 4
• 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: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.4295	0.17	1000	1.4094	110.1550
1.3042	0.34	2000	1.2886	86.2914
1.2212	0.52	3000	1.2206	84.1191
1.1306	0.69	4000	1.1814	78.1532
1.1333	0.86	5000	1.1651	76.3764

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.13.1
• Tokenizers 0.13.3