Whisper Medium Galician

This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0 gl dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2864
  • Wer: 8.4168

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: 32
  • eval_batch_size: 16
  • seed: 42
  • 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
0.0074 6.01 1000 0.2564 8.8927
0.0006 12.03 2000 0.2864 8.4168
0.0003 19.01 3000 0.3043 8.5078
0.0002 25.02 4000 0.3145 8.4913
0.0002 32.01 5000 0.3189 8.4706

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu117
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2
Downloads last month
15
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 geninhu/whisper-medium-gl

Evaluation results