ales's picture
update model card README.md
7956c2a
|
raw
history blame
1.81 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - common_voice_11_0
metrics:
  - wer
model-index:
  - name: whisper-tiny-be-test
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_11_0
          type: common_voice_11_0
          config: be
          split: validation
          args: be
        metrics:
          - name: Wer
            type: wer
            value: 75.27472527472527

whisper-tiny-be-test

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: 0.9745
  • Wer: 75.2747

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: 0.0001
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 5
  • training_steps: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
2.4473 0.5 10 1.3675 95.4212
1.256 1.0 20 0.9745 75.2747

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu116
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2