CngFSt10sec_model

This model is a fine-tuned version of openai/whisper-medium on the Marcusxx/CngFSt10sec dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0530
  • Cer: 20.6694

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: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Cer
0.0073 8.2645 1000 0.0529 75.3624
0.0007 16.5289 2000 0.0493 21.5972
0.0002 24.7934 3000 0.0510 11.1755
0.0001 33.0579 4000 0.0522 19.4764
0.0001 41.3223 5000 0.0530 20.6694

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.2.2+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
20
Safetensors
Model size
764M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for Marcusxx/CngFSt10sec_model

Finetuned
(498)
this model

Dataset used to train Marcusxx/CngFSt10sec_model