xbilek25's picture
End of training
506c98c verified
metadata
language:
  - multilingual
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: model trenovan na en-de-en not simlar setu, nastaveni jazyka en
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: xbilek25/train_set_1st_1000_de_en_de
          type: mozilla-foundation/common_voice_11_0
          args: 'config: ende, split: train'
        metrics:
          - name: Wer
            type: wer
            value: 15.042837218569435

model trenovan na en-de-en not simlar setu, nastaveni jazyka en

This model is a fine-tuned version of openai/whisper-medium on the xbilek25/train_set_1st_1000_de_en_de dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3237
  • Wer: 15.0428

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: 16
  • 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: 1
  • training_steps: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0016 7.12 2000 0.3237 15.0428

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.15.2