zeynepgulhan's picture
Update README.md
d36cc98
|
raw
history blame
1.56 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-medium-mediaspeech-cv-tr
    results: []

whisper-medium-mediaspeech-cv-tr

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: 0.1813
  • Wer: 9.9776

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: 3000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.1187 0.33 1000 0.2169 13.7678
0.0579 1.26 2000 0.1814 10.8222
0.0313 2.19 3000 0.1813 9.9776

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu117
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2