Hugging Face's logo

racheltong
/
whisper-small-custom300-1e-5-va2000

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-small-custom300-1e-5-va2000 / README.md
racheltong's picture
racheltong
End of training
ac9983a verified
preview code
|
raw history blame contribute delete
No virus
1.53 kB
metadata
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-small-custom300-1e-5-va2000
    results: []

whisper-small-custom300-1e-5-va2000

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0795
  • Wer: 1.1530

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: 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
0.0043 6.9444 1000 0.0728 1.2498
0.0003 13.8889 2000 0.0795 1.1530

Framework versions

  • Transformers 4.40.0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1