CoolFace
Modelpublic

VMadalina/whisper-large-news-augmented2

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes2downloads
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. -->

Whisper Large Ro - VM2

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

  • —Loss: 0.1650
  • —Wer: 6.0193

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: 2e-05
  • —trainbatchsize: 32
  • —evalbatchsize: 32
  • —seed: 42
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 64
  • —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 3000
  • —training_steps: 20000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.09781.206310000.144069.1424
0.05932.412520000.134919.0102
0.04793.618830000.142312.2152
0.03134.825140000.14078.6577
0.01156.031450000.14277.9429
0.00947.237660000.14447.4316
0.00638.443970000.14837.2524
0.00689.650280000.15177.2168
0.004710.856590000.15337.1072
0.002812.0627100000.15606.6211
0.002713.2690110000.15396.6994
0.001414.4753120000.15286.5063
0.001215.6815130000.15716.4202
0.000816.8878140000.15926.4315
0.000218.0941150000.15776.4602
0.000219.3004160000.15886.1907
0.000120.5066170000.16076.0776
0.021.7129180000.16216.0402
0.022.9192190000.16436.0611
0.024.1255200000.16506.0193

Framework versions

  • —Transformers 4.50.1
  • —Pytorch 2.6.0+cu124
  • —Datasets 3.4.1
  • —Tokenizers 0.21.1