README.md

metadata

language:
  - th
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - fruk19/N_asr
metrics:
  - wer
model-index:
  - name: North_asri
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: aicookcook
          type: fruk19/N_asr
          args: 'config: th'
        metrics:
          - name: Wer
            type: wer
            value: 6.260140616549487

North_asri

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

• Loss: 0.0739
• Wer: 6.2601

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 99
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.099	1.0	3000	0.1002	10.8545
0.0342	2.0	6000	0.0776	7.1390
0.0098	3.0	9000	0.0739	6.2601

Framework versions

• Transformers 4.41.2
• Pytorch 2.0.1+cu117
• Datasets 2.20.0
• Tokenizers 0.19.1