Edit model card

Whisper-Anuj-small-Malyalam-final

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1640
  • Wer: 45.0607
  • Cer: 9.4661

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: 6
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 24
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 1800

Training results

Training Loss Epoch Step Validation Loss Wer Cer
0.0563 4.3243 600 0.1279 55.3846 12.5049
0.006 8.6486 1200 0.1527 48.6640 10.2313
0.0004 12.9730 1800 0.1640 45.0607 9.4661

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
242M params
Tensor type
F32
·
Inference API
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Anujgr8/Whisper-Anuj-small-Malyalam-final

Finetuned
this model