whisper-tinyfinacialKI5002

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: 0.5267
• Wer: 63.4831

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: 400

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0.7937	50	0.9182	64.6067
No log	1.5873	100	0.6586	63.4831
No log	2.3810	150	0.5617	68.5393
No log	3.1746	200	0.5066	58.4270
No log	3.9683	250	0.5154	58.4270
No log	4.7619	300	0.5253	55.0562
No log	5.5556	350	0.5301	60.1124
No log	6.3492	400	0.5267	63.4831

Framework versions

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