whisper-small-tamil / README.md
sujith013's picture
End of training
59b3203
metadata
language:
  - ta
license: apache-2.0
base_model: openai/whisper-small
tags:
  - Tamil-ASR
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper-Small-Tamil
    results: []

Whisper-Small-Tamil

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

  • Loss: 0.0128
  • Wer: 17.0413

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: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 50
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.1713 4.39 250 0.0533 28.5519
0.0291 8.77 500 0.0128 17.0413

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.0.0
  • Datasets 2.1.0
  • Tokenizers 0.14.1