whisper-large-marathi

This model is a fine-tuned version of openai/whisper-large on the Common Voice 17 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1845
  • Wer Ortho: 32.4713
  • Wer: 11.9958

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: 12
  • 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: 20
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer Ortho Wer
0.1771 1.0 250 0.2041 36.0371 13.7851
0.0806 2.0 500 0.1845 32.4713 11.9958

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.5.0+cu121
  • Datasets 3.1.0
  • Tokenizers 0.19.1
Downloads last month
26
Safetensors
Model size
1.54B params
Tensor type
F32
·
Inference Examples
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 durgesh10/whisper-large-marathi

Finetuned
(53)
this model

Dataset used to train durgesh10/whisper-large-marathi

Evaluation results