Arbi-Houssem/TunLangModel_test1.17

Whisper Tunisien

This model is a fine-tuned version of openai/whisper-small on the Tunisian_dataset_STT-TTS15s_filtred1.0_Mixed dataset. It achieves the following results on the evaluation set:

• Loss: 1.3057
• Wer: 45.3307

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: 0.0001
• train_batch_size: 8
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3483	4.5045	500	1.0341	53.6221
0.1138	9.0090	1000	1.1225	49.9641
0.0476	13.5135	1500	1.1610	51.5278
0.0238	18.0180	2000	1.2585	48.0993
0.007	22.5225	2500	1.2873	51.6282
0.0021	27.0270	3000	1.2722	46.8656
0.0007	31.5315	3500	1.2998	43.5375
0.0006	36.0360	4000	1.3057	45.3307

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1