Team Ai
Modelpublic

Eimhin03/output_model_shunyalabs_data_base_model_proper_feature_extractor_more

sourceHugging Faceapache-2.0updated 8mo agoView on Hugging Face
0likes9downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

outputmodelshunyalabsdatabasemodelproperfeatureextractor_more

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

  • —Loss: 0.6676
  • —Wer: 25.3729

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: 0.0001
  • —trainbatchsize: 2
  • —evalbatchsize: 4
  • —seed: 42
  • —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 40000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.63061.953125000.808852.2670
0.28023.906250000.720039.6101
0.09195.859475000.701441.1018
0.07117.8125100000.733436.9960
0.05229.7656125000.697134.1161
0.044011.7188150000.712932.5949
0.015913.6719175000.749233.7912
0.017415.625200000.717031.4577
0.009317.5781225000.710730.3205
0.003519.5312250000.709628.4301
0.003221.4844275000.696028.2824
0.000423.4375300000.674628.6516
0.000125.3906325000.686326.5987
0.000027.3438350000.677626.3624
0.000029.2969375000.674025.7421
0.000031.25400000.667625.3729

Framework versions

  • —Transformers 5.0.0
  • —Pytorch 2.9.0+cu126
  • —Datasets 4.0.0
  • —Tokenizers 0.22.2