mikr/whisper-medium-sl-cv11

Whisper Medium Slovenian CV11

This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0 sl dataset. It achieves the following results on the evaluation set:

• Loss: 0.4331
• Wer: 17.9300

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: 32
• seed: 42
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.003	26.32	1000	0.3665	19.0379
0.0001	52.63	2000	0.4114	18.1778
0.0001	78.95	3000	0.4331	17.9300
0.0	105.26	4000	0.4458	18.0321
0.0	131.58	5000	0.4512	17.9883

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2