<!-- 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-53-english-pronunciation-evaluation-ep-v1
This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-english on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4314
- Accuracy: 0.794
- F1: 0.7952
- Precision: 0.7979
- Recall: 0.794
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
1.2102 | 1.0 | 1000 | 0.8911 | 0.558 | 0.5435 | 0.5637 | 0.558 |
0.5611 | 2.0 | 2000 | 0.6968 | 0.698 | 0.6948 | 0.7032 | 0.698 |
0.711 | 3.0 | 3000 | 1.3072 | 0.65 | 0.6307 | 0.6577 | 0.65 |
0.3093 | 4.0 | 4000 | 1.0841 | 0.744 | 0.7410 | 0.7547 | 0.744 |
0.8599 | 5.0 | 5000 | 1.2025 | 0.762 | 0.7610 | 0.7853 | 0.762 |
0.1832 | 6.0 | 6000 | 1.1577 | 0.796 | 0.7929 | 0.7961 | 0.796 |
0.491 | 7.0 | 7000 | 1.3036 | 0.818 | 0.8183 | 0.8190 | 0.818 |
0.0003 | 8.0 | 8000 | 1.4549 | 0.814 | 0.8137 | 0.8147 | 0.814 |
0.0002 | 9.0 | 9000 | 1.5854 | 0.802 | 0.8022 | 0.8055 | 0.802 |
0.195 | 10.0 | 10000 | 1.6096 | 0.798 | 0.7979 | 0.7984 | 0.798 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3