README.md

metadata

language:
  - th
license: apache-2.0
tags:
  - generated_from_trainer
base_model: openai/whisper-small
datasets:
  - aicookcook
metrics:
  - wer
model-index:
  - name: all_asr
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: aicookcook
          type: aicookcook
          args: config:th
        metrics:
          - type: wer
            value: 18.262970669172425
            name: Wer

all_asr

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: 0.1879
• Wer: 18.2630

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: 5
• eval_batch_size: 5
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0586	3.0048	2500	0.1755	19.9779
0.0038	6.0096	5000	0.1879	18.2630

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1