tamasheq-99-1 / README.md
ad019el's picture
update model card README.md
9e4ec58
metadata
license: apache-2.0
base_model: jonatasgrosman/wav2vec2-large-xlsr-53-arabic
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: tamasheq-5
    results: []

tamasheq-5

This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-arabic on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2985
  • Wer: 0.4870

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: 3e-05
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss Wer
10.0913 6.06 400 3.0405 1.0
1.2281 12.12 800 0.3682 0.5056
0.3094 18.18 1200 0.3076 0.4878
0.2389 24.24 1600 0.2985 0.4870

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3