Hugging Face's logo

justanotherinternetguy
/
whisper-small-sep28

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-small-sep28 / README.md
justanotherinternetguy's picture
justanotherinternetguy
End of training
e5dfbae verified
preview code
|
raw
history blame contribute delete
1.85 kB
metadata
library_name: transformers
language:
  - en
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper-Small Augmented for SEP-28k
    results: []

Whisper-Small Augmented for SEP-28k

This model is a fine-tuned version of openai/whisper-small on the SEP-28K dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7265
  • Wer: 13.7591

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: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 5910
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0229 5.1020 1000 0.5061 13.5547
0.0018 10.2041 2000 0.6259 13.6204
0.0006 15.3061 3000 0.6754 13.6496
0.0005 20.4082 4000 0.7105 13.7007
0.0004 25.5102 5000 0.7265 13.7591

Framework versions

  • Transformers 4.47.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0