<!-- 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-xlsr-persian4-demo
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: 0.4691
- Wer: 0.5166
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: 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: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
3.2175 | 1.0 | 400 | 3.0445 | 1.0 |
1.6533 | 2.0 | 800 | 1.3703 | 0.9333 |
0.7507 | 3.0 | 1200 | 0.6387 | 0.6474 |
0.5435 | 4.0 | 1600 | 0.5102 | 0.5506 |
0.5017 | 5.0 | 2000 | 0.4691 | 0.5166 |
Framework versions
- Transformers 4.22.0.dev0
- Pytorch 1.11.0+cu102
- Datasets 2.4.1.dev0
- Tokenizers 0.12.1