whisper-tiny-en

This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5089
• Wer: 31.4721

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4475	10.53	100	0.6788	20.5584
0.0166	21.05	200	0.4262	19.2893
0.0005	31.58	300	0.4534	22.8426
0.0003	42.11	400	0.4673	68.7817
0.0002	52.63	500	0.4806	72.5888
0.0002	63.16	600	0.4908	72.3350
0.0001	73.68	700	0.4987	31.4721
0.0001	84.21	800	0.5045	31.4721
0.0001	94.74	900	0.5078	31.4721
0.0001	105.26	1000	0.5089	31.4721

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1