README.md

metadata

library_name: transformers
language:
  - en
license: mit
base_model: distil-whisper/distil-large-v3
tags:
  - generated_from_trainer
datasets:
  - lelapa/www_call_center_merged_en_corrected
metrics:
  - wer
model-index:
  - name: Distill Whisper Call Center Tforge Dev lr3
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: www_call_center_merged_en_corrected
          type: lelapa/www_call_center_merged_en_corrected
          args: 'config: en, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 44.3461781427669

Distill Whisper Call Center Tforge Dev lr3

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

• Loss: 1.6777
• Wer: 44.3462

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: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1582	3.0722	1000	1.3541	42.8617
0.0574	6.1444	2000	1.6777	44.3462

Framework versions

• Transformers 4.45.2
• Pytorch 2.7.0+cu126
• Datasets 3.6.0
• Tokenizers 0.20.3