whisper-small-tr-istech

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: 0.2332
• Wer: 43.7858

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: 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
0.1308	0.8857	1000	0.2348	29.2727
0.0622	1.7715	2000	0.2234	28.4827
0.0286	2.6572	3000	0.2207	33.5197
0.0122	3.5430	4000	0.2262	38.4285
0.0059	4.4287	5000	0.2332	43.7858

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1