whisper-tinyfinacialKI

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: 0.5532
• Wer: 62.9213

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: 1.35e-05
• train_batch_size: 8
• 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: 100
• training_steps: 1200

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0.7519	100	0.7072	71.3483
No log	1.5038	200	0.5276	51.1236
No log	2.2556	300	0.4869	47.7528
No log	3.0075	400	0.4923	43.8202
0.3216	3.7594	500	0.5228	57.3034
0.3216	4.5113	600	0.5561	52.8090
0.3216	5.2632	700	0.5168	55.6180
0.3216	6.0150	800	0.5289	64.0449
0.3216	6.7669	900	0.5541	57.3034
0.0049	7.5188	1000	0.5548	62.3596
0.0049	8.2707	1100	0.5499	63.4831
0.0049	9.0226	1200	0.5532	62.9213

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1