Edit model card

Whisper Small Malayalam - Arjun Shaji

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5649
  • Wer: 83.9080

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: 100
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.8113 3.7037 100 0.5609 100.6897
0.1123 7.4074 200 0.4366 88.0460
0.0184 11.1111 300 0.4850 87.1264
0.0056 14.8148 400 0.5643 87.8161
0.001 18.5185 500 0.5649 83.9080

Framework versions

  • Transformers 4.41.0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
13
Safetensors
Model size
242M params
Tensor type
F32
·

Finetuned from

Dataset used to train arjunshajitech/whisper-small-malayalam-v1

Evaluation results