Hugging Face's logo

kwspringkles
/
whisper_medium_10epochs

Transformers
Safetensors
Generated from Trainer
Model card Files
xet
 Community

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

whisper_medium_10epochs

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

  • Loss: 0.7202
  • Cer: 23.6602

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: 3e-06
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: reduce_lr_on_plateau
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Cer
0.56 1.0 1262 0.6154 25.4159
0.4757 2.0 2524 0.6130 24.4768
0.4172 3.0 3786 0.6231 20.8906
0.355 4.0 5048 0.6491 24.1614
0.2963 5.0 6310 0.6801 24.6065
0.2755 6.0 7572 0.7202 23.6602

Framework versions

  • Transformers 4.56.1
  • Pytorch 2.8.0+cu129
  • Datasets 4.0.0
  • Tokenizers 0.22.0
Downloads last month
-
Safetensors
Model size
0.8B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kwspringkles/whisper_medium_10epochs

Base model

openai/whisper-medium
Finetuned
(890)
this model