lelapa/distill_whisper_call_center_en_merged

Distill Whisper Call Center

This model is a fine-tuned version of distil-whisper/distil-large-v3 on the www_call_center_eng_merged_v2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6973
• Wer: 16.3948

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: 8
• eval_batch_size: 8
• 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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1908	3.0211	1000	0.3349	15.6292
0.0686	6.0423	2000	0.4456	16.3675
0.0136	9.0634	3000	0.6066	16.6109
0.0024	12.0846	4000	0.6973	16.3948

Framework versions

• Transformers 4.45.2
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.20.3