README.md

metadata

language:
  - km
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - openslr
metrics:
  - wer
model-index:
  - name: Whisper Large Khmer - Kak Soky
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: SLR42
          type: openslr
          args: 'config: km, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 29.51830443159923

Whisper Large Khmer - Kak Soky

This model is a fine-tuned version of openai/whisper-large on the SLR42 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2375
• Wer: 29.5183

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: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0102	12.34	1000	0.2228	38.2659
0.0003	24.69	2000	0.2260	30.7900
0.0001	37.04	3000	0.2310	30.0578
0.0	49.38	4000	0.2375	29.5183

Framework versions

• Transformers 4.25.0.dev0
• Pytorch 1.9.1+cu111
• Datasets 2.3.2
• Tokenizers 0.12.1