whisper-tinyfinacialYT

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: 0.8105
• Wer: 64.6067

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	1.0870	100	0.7181	65.1685
No log	2.1739	200	0.6369	60.6742
No log	3.2609	300	0.6620	60.6742
No log	4.3478	400	0.6909	61.7978
0.3822	5.4348	500	0.7271	73.0337
0.3822	6.5217	600	0.7496	71.3483
0.3822	7.6087	700	0.7742	64.0449
0.3822	8.6957	800	0.7860	64.0449
0.3822	9.7826	900	0.7975	64.0449
0.0087	10.8696	1000	0.8065	64.6067
0.0087	11.9565	1100	0.8098	64.6067
0.0087	13.0435	1200	0.8105	64.6067

Framework versions

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