metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: egy-slang-model
results: []
egy-slang-model
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9538
- Wer: 0.9996
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: 0.001
- 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
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
3.7978 | 3.28 | 400 | 2.9727 | 1.0 |
2.9541 | 6.56 | 800 | 2.9667 | 1.0 |
2.9529 | 9.83 | 1200 | 2.9739 | 0.9999 |
2.9228 | 13.11 | 1600 | 2.9690 | 0.9999 |
2.8879 | 16.39 | 2000 | 3.0275 | 1.0 |
2.8703 | 19.67 | 2400 | 3.0226 | 0.9999 |
2.8552 | 22.95 | 2800 | 2.9886 | 0.9999 |
2.8397 | 26.23 | 3200 | 2.9590 | 0.9999 |
2.8026 | 29.51 | 3600 | 2.9538 | 0.9996 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.1
- Datasets 1.13.3
- Tokenizers 0.10.3