<!-- 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-arabic-no-diacs_V1
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.2894
- Wer: 0.2470
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.6563 | 0.83 | 1000 | 0.5231 | 0.5077 |
0.4532 | 1.66 | 2000 | 0.3642 | 0.3588 |
0.2687 | 2.5 | 3000 | 0.3245 | 0.2920 |
0.1846 | 3.33 | 4000 | 0.3050 | 0.2640 |
0.1587 | 4.16 | 5000 | 0.2894 | 0.2470 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.10.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1