Whisper Medium Swedish
This model is a fine-tuned version of Whisper Medium Nordic on the mozilla-foundation/common_voice_11_0 (train+validation), the babelbox/babelbox_voice (NST SV - train split) and the google/fleurs (sv_se - train+validation+test) datasets. It achieves the following results on the evaluation set:
- eval_loss: 0.2483
- eval_wer: 9.8914
- eval_runtime: 2924.8709
- eval_samples_per_second: 1.733
- eval_steps_per_second: 0.108
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: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 250
- training_steps: 5000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2
WandB run
https://wandb.ai/pn-aa/whisper/runs/z2lzjx4x?workspace=user-emilio_marinone
- Downloads last month
- 4
Datasets used to train marinone94/whisper-medium-swedish
Evaluation results
- Wer on mozilla-foundation/common_voice_11_0test set self-reported9.890