CoolFace
Modelpublic

infinitejoy/wav2vec2-large-xls-r-300m-romansh-vallader

sourceHugging Faceapache-2.0updated 5y agoView on Hugging Face
0likes55downloads
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-large-xls-r-300m-romansh-vallader

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMONVOICE7_0 - RM-VALLADER dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.3155
  • —Wer: 0.3162

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: 7e-05
  • —trainbatchsize: 32
  • —evalbatchsize: 1
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —num_epochs: 100.0
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
2.955615.625002.93001.0
1.787431.2510000.75660.6509
1.013146.8815000.36710.3828
0.843962.520000.33500.3416
0.750278.1225000.31550.3296
0.709393.7530000.31820.3186

Framework versions

  • —Transformers 4.16.0.dev0
  • —Pytorch 1.10.1+cu102
  • —Datasets 1.17.1.dev0
  • —Tokenizers 0.11.0