Hugging Face's logo

crossdelenna
/
whisper-medium.en

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-medium.en / README.md
crossdelenna's picture
crossdelenna
End of training
f49d1e6 verified
preview code
|
raw
history blame contribute delete
1.53 kB
metadata
license: apache-2.0
base_model: crossdelenna/whisper-medium.en
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-medium.en
    results: []

whisper-medium.en

This model is a fine-tuned version of crossdelenna/whisper-medium.en on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0261
  • Wer: 2.4421

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: 6
  • eval_batch_size: 6
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 10
  • training_steps: 800
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0446 0.3872 400 0.0520 4.2961
0.0387 0.7744 800 0.0261 2.4421

Framework versions

  • Transformers 4.43.0.dev0
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1