enniorampello/whisper-small-hi

Whisper Small Hi - Swedish

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3953
• Wer: 19.6472

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: 500
• training_steps: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1331	1.29	1000	0.3014	22.3602
0.0537	2.59	2000	0.2988	20.8572
0.0217	3.88	3000	0.3093	20.5641
0.004	5.17	4000	0.3551	20.0479
0.0015	6.47	5000	0.3701	20.0022
0.0015	7.76	6000	0.3769	19.7386
0.0007	9.06	7000	0.3908	19.7010
0.0006	10.35	8000	0.3953	19.6472

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.9.0+cu102
• Datasets 2.7.1
• Tokenizers 0.13.2