whisper-small-tr

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: 0.2316
• Wer: 20.0886

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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2284	0.3447	1000	0.2814	23.9819
0.1906	0.6894	2000	0.2606	22.5598
0.0945	1.0341	3000	0.2472	21.1990
0.0871	1.3788	4000	0.2405	20.6744
0.0823	1.7235	5000	0.2316	20.0886

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu124
• Datasets 3.0.0
• Tokenizers 0.19.1