Edit model card

ArabicSpeechToText

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

  • Loss: 0.3207
  • Wer: 0.2901

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: 0.0003
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 8
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
5.6589 0.52 700 0.8361 0.7598
0.7367 1.03 1400 0.5243 0.4771
0.479 1.55 2100 0.4025 0.3756
0.3742 2.06 2800 0.3651 0.3272
0.2846 2.58 3500 0.3207 0.2901

Framework versions

  • Transformers 4.11.3
  • Pytorch 1.10.0+cu113
  • Datasets 2.9.0
  • Tokenizers 0.10.3
Downloads last month
24
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train Foxasdf/ArabicSpeechToText