Huseyin/whisper-small-tr

Whisper Small Tr - Huseyin Ates

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2347
• Wer: 20.4616

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: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2284	0.3447	1000	0.2800	23.8695
0.1868	0.6894	2000	0.2569	22.2992
0.0948	1.0341	3000	0.2410	20.9929
0.0865	1.3788	4000	0.2347	20.4616

Framework versions

• Transformers 4.41.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1