tahaman/whisper-small-ur

Whisper Small Ur - TahaMan

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: 0.9384
• Wer: 47.2296

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• training_steps: 400
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.7769	5.2632	50	0.7217	62.9288
0.1271	10.5263	100	0.7884	62.4011
0.0149	15.7895	150	0.8567	48.0211
0.0039	21.0526	200	0.8914	47.2296
0.0024	26.3158	250	0.9138	47.2296
0.0018	31.5789	300	0.9278	47.2296
0.0016	36.8421	350	0.9357	46.9657
0.0014	42.1053	400	0.9384	47.2296

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1