Hugging Face's logo

Team-ASR-2023
/
wav2vec2-large-xls-r-300m-Arabic

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
2
wav2vec2-large-xls-r-300m-Arabic / README.md
nrshoudi's picture
nrshoudi
update model card README.md
77aa507
preview code
|
raw
history blame
3.55 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: wav2vec2-large-xls-r-300m-Arabic-colab
    results: []

wav2vec2-large-xls-r-300m-Arabic-colab

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0001
  • Wer: 0.0813
  • Cer: 0.0362

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: 0.0005
  • train_batch_size: 16
  • eval_batch_size: 6
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 250
  • num_epochs: 30.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer Cer
0.0166 1.0 51 0.0020 0.0944 0.0431
0.015 2.0 102 0.0018 0.0939 0.0434
0.0223 3.0 153 0.0034 0.0705 0.0311
0.0351 4.0 204 0.0089 0.1050 0.0414
0.0473 5.0 255 0.0051 0.1224 0.0614
0.0406 6.0 306 0.0084 0.1185 0.0547
0.0412 7.0 357 0.0030 0.0640 0.0254
0.0301 8.0 408 0.0157 0.0708 0.0219
0.0295 9.0 459 0.0027 0.0716 0.0298
0.0239 10.0 510 0.0077 0.0868 0.0354
0.0266 11.0 561 0.0017 0.0733 0.0301
0.0154 12.0 612 0.0015 0.0961 0.0385
0.0187 13.0 663 0.0006 0.1100 0.0465
0.0156 14.0 714 0.0015 0.1030 0.0426
0.013 15.0 765 0.0014 0.1068 0.0451
0.0136 16.0 816 0.0013 0.1066 0.0434
0.0123 17.0 867 0.0008 0.1240 0.0587
0.0098 18.0 918 0.0006 0.1140 0.0570
0.0108 19.0 969 0.0005 0.0843 0.0364
0.009 20.0 1020 0.0002 0.0954 0.0438
0.0083 21.0 1071 0.0003 0.0828 0.0377
0.0085 22.0 1122 0.0002 0.0648 0.0267
0.0073 23.0 1173 0.0003 0.0843 0.0373
0.0057 24.0 1224 0.0003 0.0822 0.0367
0.0039 25.0 1275 0.0002 0.0733 0.0329
0.0045 26.0 1326 0.0005 0.0754 0.0335
0.008 27.0 1377 0.0008 0.0803 0.0361
0.0045 28.0 1428 0.0001 0.0772 0.0340
0.0043 29.0 1479 0.0001 0.0808 0.0359
0.0042 30.0 1530 0.0001 0.0813 0.0362

Framework versions

  • Transformers 4.26.1
  • Pytorch 1.13.1+cu116
  • Datasets 2.9.0
  • Tokenizers 0.13.2