whisperFinetuneFinal

This model is a fine-tuned version of openai/whisper-tiny.en on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5711
• Wer: 22.2920

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: 0.001
• train_batch_size: 128
• 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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.8037	0.2778	10	1.8972	34.0973
0.8101	0.5556	20	0.6863	28.6970
0.5778	0.8333	30	0.5491	22.8885
0.4375	1.1111	40	0.4962	20.7535
0.3437	1.3889	50	0.4767	20.2512
0.3277	1.6667	60	0.4921	21.0047
0.3431	1.9444	70	0.4972	20.4082
0.1331	2.2222	80	0.5317	25.7143
0.1385	2.5	90	0.5308	20.4396
0.146	2.7778	100	0.5711	22.2920

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.1.dev0
• Tokenizers 0.19.1