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