CoolFace
Modelpublic

davidilag/wav2vec2-xls-r-1b-scandinavian-E6-25h-30-epochs-20250208_v6

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes8downloads
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. -->

wav2vec2-xls-r-1b-scandinavian-E6-25h-30-epochs-20250208_v6

This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: inf
  • —Wer: 30.3141
  • —Cer: 10.6693

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: 16
  • —evalbatchsize: 8
  • —seed: 42
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 32
  • —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 5000
  • —num_epochs: 30
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWerCer
1.15570.80521000inf82.293129.3959
1.20641.61032000inf60.040020.7421
1.00982.41553000inf51.438717.2982
0.57773.22064000inf50.082016.9330
0.40354.02585000inf49.739216.9217
0.41484.83096000inf48.694716.5653
0.39095.63617000inf47.216716.1521
0.39576.44128000inf46.793815.9950
0.51957.24649000inf45.672015.6448
0.49778.051510000inf41.339314.0356
0.47938.856711000inf41.271314.0323
0.41759.661812000inf40.518913.7936
0.260210.467013000inf38.570013.2449
0.256611.272114000inf37.897713.0691
0.221512.077315000inf39.287713.5549
0.255712.882416000inf37.851012.8671
0.367213.687617000inf38.666013.1300
0.328214.492818000inf37.348112.7591
0.310115.297919000inf35.903412.3669
0.182116.103120000inf35.009712.1182
0.171916.908221000inf35.775412.4047
0.152917.713422000inf34.903012.0927
0.133818.518523000inf34.304011.8955
0.218619.323724000inf33.549011.7366
0.231120.128825000inf33.346211.5700
0.230620.934026000inf32.676611.3913
0.226721.739127000inf33.304911.4791
0.138122.544328000inf32.160311.2660
0.083823.349429000inf32.091011.2171
0.082124.154630000inf31.250610.9537
0.07724.959731000inf31.086510.9077
0.124825.764932000inf30.621010.7582
0.154826.570033000inf30.742310.8239
0.164827.375234000inf30.290110.6713
0.130328.180435000inf30.367510.6884
0.13528.985536000inf30.307510.6664
0.06229.790737000inf30.314110.6693

Framework versions

  • —Transformers 4.48.2
  • —Pytorch 2.5.1+cu124
  • —Datasets 3.2.0
  • —Tokenizers 0.21.0