deepdml/whisper-base-en-cv17

Whisper Medium en

This model is a fine-tuned version of openai/whisper-base on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5062
• Wer: 19.8143

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: 64
• 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: 500
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3654	1.0974	1000	0.5075	20.6605
0.2314	3.0922	2000	0.5117	20.1370
0.261	5.087	3000	0.5058	20.1230
0.1793	7.0818	4000	0.5196	20.5831
0.2344	9.0766	5000	0.5062	19.8143

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1