idaracecilia/whisper-finetuned-base

Whisper Fine tuned Base

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

• Loss: 0.3550
• Wer: 15.0186

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 5
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3123	0.5	25	0.4652	20.1147
0.3282	1.0	50	0.3655	16.2673
0.0376	1.5	75	0.3693	15.4573
0.0468	2.0	100	0.3754	20.2497
0.0067	2.5	125	0.3585	15.3898
0.0098	3.0	150	0.3550	15.0186

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1