UsmanAXAI/whisper-medium-ft-client

Whisper Medium Ar - AxAI

This model is a fine-tuned version of openai/whisper-medium on the Client dataset. It achieves the following results on the evaluation set:

• Loss: 3.5466
• Wer: 100.0

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: 1e-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0411	24.39	500	2.8748	100.0
0.0063	48.78	1000	3.3347	100.0
0.0017	73.17	1500	3.4076	100.0
0.0003	97.56	2000	3.4587	100.0
0.0001	121.95	2500	3.5256	100.0
0.0001	146.34	3000	3.5325	100.0
0.0001	170.73	3500	3.5419	100.0
0.0001	195.12	4000	3.5466	100.0

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2