Luganda_speech_to_intent_wav2vec_xlsr_1
This model is a fine-tuned version of KasuleTrevor/wav2vec2-large-xls-r-300m-lg-cv-130hr-v1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1759
- Accuracy: 0.9766
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.8819 | 1.0 | 131 | 1.4887 | 0.7820 |
1.2141 | 2.0 | 262 | 0.1202 | 0.9913 |
0.2148 | 3.0 | 393 | 0.0676 | 0.9913 |
0.1365 | 4.0 | 524 | 0.0831 | 0.9881 |
0.124 | 5.0 | 655 | 0.0793 | 0.9892 |
0.126 | 6.0 | 786 | 0.0692 | 0.9837 |
0.1079 | 7.0 | 917 | 0.0594 | 0.9913 |
0.0794 | 8.0 | 1048 | 0.0637 | 0.9902 |
0.0867 | 9.0 | 1179 | 0.0641 | 0.9902 |
0.0652 | 10.0 | 1310 | 0.0822 | 0.9859 |
0.0618 | 11.0 | 1441 | 0.0661 | 0.9892 |
0.0484 | 12.0 | 1572 | 0.0679 | 0.9892 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.0+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 0