README.md

metadata

library_name: transformers
language:
  - km
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - Khmer_speech_dataset
metrics:
  - wer
model-index:
  - name: Whisper Small Hi - Sanchit Gandhi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Khmer_voice
          type: Khmer_speech_dataset
          args: 'config: km, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 79.34426229508198

Whisper Small Hi - Sanchit Gandhi

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

• Loss: 0.6083
• Wer: 79.3443

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3396	0.2899	200	0.6831	119.3443
0.1706	0.5797	400	0.6083	79.3443

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1