alikanakar/whisper-small-CV-43

Whisper Small Tr - CV 43h

This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2371
• Wer: 20.1024

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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
0.2134	0.37	500	0.2739	23.3965
0.1845	0.73	1000	0.2587	22.2823
0.1056	1.1	1500	0.2445	21.1214
0.1009	1.46	2000	0.2413	20.7278
0.0963	1.83	2500	0.2329	20.0952
0.0555	2.19	3000	0.2389	20.4421
0.0577	2.56	3500	0.2387	20.2588
0.0512	2.92	4000	0.2371	20.1024

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2