README.md

metadata

language:
  - ml
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - thennal/GMaSC
metrics:
  - wer
model-index:
  - name: Whisper Small Malayalam - Arjun Shaji
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: thennal/GMaSC
          type: thennal/GMaSC
          args: 'config: ml, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 16.95364238410596

Whisper Small Malayalam - Arjun Shaji

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

• Loss: 0.0505
• Wer: 16.9536

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: 16
• eval_batch_size: 8
• 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
0.0022	10.0	1000	0.0410	18.0132
0.0002	20.0	2000	0.0454	17.6159
0.0	30.0	3000	0.0486	17.2185
0.0	40.0	4000	0.0499	17.1302
0.0	50.0	5000	0.0505	16.9536

Framework versions

• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1