whisper-medium-he / README.md
imvladikon's picture
End of training
4d5e5ab
|
raw
history blame
1.73 kB
metadata
language:
  - he
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-medium-he
    results: []

whisper-medium-he

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

  • Loss: 0.2042
  • Wer: 12.9071

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: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 2
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.1865 0.1 1000 0.3587 21.4973
0.2601 0.2 2000 0.2673 17.1157
0.2033 0.3 3000 0.2238 14.4325
0.1988 0.39 4000 0.2042 12.9071

Framework versions

  • Transformers 4.36.0.dev0
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0