Edit model card

whisper-medium-hi

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

  • Loss: 0.3957
  • Wer: 0.2425

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: 16
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • total_train_batch_size: 32
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0234 4.88 1000 0.2762 0.2750
0.003 9.76 2000 0.3342 0.2518
0.0001 14.63 3000 0.3636 0.2424
0.0 19.51 4000 0.3877 0.2426
0.0 24.39 5000 0.3957 0.2425

Framework versions

  • Transformers 4.28.0.dev0
  • Pytorch 2.0.0+cu117
  • Datasets 2.11.0
  • Tokenizers 0.13.3
Downloads last month
6
Inference API
or
This model can be loaded on Inference API (serverless).

Space using tarunanand/whisper-medium-hi 1