metadata
license: apache-2.0
base_model: jonatasgrosman/wav2vec2-large-xlsr-53-arabic
tags:
- generated_from_trainer
datasets:
- common_voice
model-index:
- name: tamasheq-99
results: []
tamasheq-99
This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-arabic on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.1909
- Cer: 0.1316
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 | Cer |
|---|---|---|---|---|
| 11.1661 | 6.0 | 300 | 3.1963 | 0.9694 |
| 2.5713 | 12.0 | 600 | 0.5591 | 0.1554 |
| 0.4775 | 18.0 | 900 | 0.2220 | 0.1275 |
| 0.3081 | 24.0 | 1200 | 0.1992 | 0.1284 |
| 0.27 | 30.0 | 1500 | 0.1909 | 0.1316 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3