Edit model card

openai/whisper-small-Assamese

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: 0.7523
  • Wer: 42.1075

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: 8
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.2518 20.01 250 0.5376 143.3410
0.0069 41.01 500 0.6409 49.9268
0.0004 62.01 750 0.7344 43.4455
0.0001 83.0 1000 0.7523 42.1075

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.11.0
  • Datasets 2.1.0
  • Tokenizers 0.12.1
Downloads last month
8

Dataset used to train kpriyanshu256/whisper-small-as-1000-64-1e-05

Evaluation results