metadata
library_name: transformers
language:
- en
license: mit
base_model: distil-whisper/distil-large-v3
tags:
- generated_from_trainer
datasets:
- Jenalea/www_call_center_en_merged
metrics:
- wer
model-index:
- name: Distill Whisper Call Center
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: www_call_center_eng_merged
type: Jenalea/www_call_center_en_merged
args: 'config: en, split: test'
metrics:
- name: Wer
type: wer
value: 15.436723341258803
Distill Whisper Call Center
This model is a fine-tuned version of distil-whisper/distil-large-v3 on the www_call_center_eng_merged dataset. It achieves the following results on the evaluation set:
- Loss: 0.6325
- Wer: 15.4367
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 |
|---|---|---|---|---|
| 0.1595 | 3.0628 | 1000 | 0.3259 | 14.9904 |
| 0.0579 | 6.1256 | 2000 | 0.4136 | 15.3033 |
| 0.0121 | 9.1884 | 3000 | 0.5519 | 15.2943 |
| 0.0021 | 12.2511 | 4000 | 0.6325 | 15.4367 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.6.0+cu124
- Datasets 3.4.0
- Tokenizers 0.20.3