whisper-tiny-ro / README.md
giigii91's picture
End of training
a19b420 verified
metadata
language:
  - ro
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Tiny RO - Georgescu Dumitru
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: ro
          split: test
          args: ro
        metrics:
          - name: Wer
            type: wer
            value: 100.5201330408322

Whisper Tiny RO - Georgescu Dumitru

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: 0.8465
  • Wer: 100.5201

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: 64
  • eval_batch_size: 8
  • 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
0.0437 12.0032 1000 0.6372 125.1044
0.0037 24.0064 2000 0.7549 107.4234
0.0016 36.0096 3000 0.8043 101.3233
0.001 48.0128 4000 0.8338 101.0297
0.0008 60.016 5000 0.8465 100.5201

Framework versions

  • Transformers 4.42.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.2.dev0
  • Tokenizers 0.19.1