README.md

metadata

language:
  - th
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small Thai
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0 th
          type: mozilla-foundation/common_voice_11_0
          config: th
          split: test
          args: th
        metrics:
          - name: Wer
            type: wer
            value: 29.169
          - name: Mer
            type: mer
            value: 27.781

Whisper Small Thai

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 th dataset. It achieves the following results on the evaluation set:

• Loss: 0.3703
• Wer: 90.9836

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-07
• train_batch_size: 64
• eval_batch_size: 32
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4319	2.0	1000	0.4203	97.5410
0.4003	4.0	2000	0.3933	95.0820
0.3844	6.0	3000	0.3800	93.0328
0.3876	8.0	4000	0.3729	91.8033
0.3899	10.0	5000	0.3703	90.9836

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2