mother_tongue_model_v3

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

• Loss: 0.0000
• Wer: 0.0

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: 1
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0018	16.3934	500	0.0009	0.0
0.0001	32.7869	1000	0.0001	0.0
0.0	49.1803	1500	0.0001	0.0
0.0	65.5738	2000	0.0000	0.0
0.0	81.9672	2500	0.0000	0.0
0.0	98.3607	3000	0.0000	0.0
0.0	114.7541	3500	0.0000	0.0
0.0	131.1475	4000	0.0000	0.0
0.0	147.5410	4500	0.0000	0.0
0.0	163.9344	5000	0.0000	0.0

Framework versions

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