whisper-small-hy / README.md
lalacelik's picture
End of training
aec8a77 verified
metadata
library_name: transformers
language:
  - hy
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
metrics:
  - wer
model-index:
  - name: 'Whisper Small Hy '
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 17.0
          type: mozilla-foundation/common_voice_17_0
          config: hy-AM
          split: None
          args: 'config: hy, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 40.02161383285303

Whisper Small Hy

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1879
  • Wer: 40.0216

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
  • 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
0.3648 0.0962 1000 0.3407 62.9623
0.3011 0.1924 2000 0.2642 52.0023
0.2238 0.2886 3000 0.2272 46.9831
0.2294 0.3848 4000 0.2010 42.8945
0.1745 0.4810 5000 0.1879 40.0216

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1