whisper-tiny-hi

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

  • Loss: 0.7990
  • Wer: 43.8869

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
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 3000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.1747 7.02 1000 0.5674 41.6800
0.0466 14.03 2000 0.7042 43.7378
0.0174 22.0 3000 0.7990 43.8869

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.10.0
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2
Downloads last month
31
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.

Dataset used to train amitkayal/whisper-tiny-hi

Space using amitkayal/whisper-tiny-hi 1

Evaluation results