wav2vec2-base-lang-id
This model is a fine-tuned version of facebook/wav2vec2-base on the common_language dataset. It achieves the following results on the evaluation set:
- Loss: 1.6572
- Accuracy: 0.5802
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: 32
- eval_batch_size: 4
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.5548 | 1.0 | 173 | 3.6911 | 0.0659 |
| 2.9779 | 2.0 | 346 | 3.0769 | 0.2024 |
| 2.4706 | 3.0 | 519 | 2.6689 | 0.2964 |
| 2.0118 | 4.0 | 692 | 2.3199 | 0.4234 |
| 1.6745 | 5.0 | 865 | 2.1130 | 0.4650 |
| 1.3753 | 6.0 | 1038 | 1.9451 | 0.5156 |
| 1.1559 | 7.0 | 1211 | 1.8114 | 0.5442 |
| 1.0208 | 8.0 | 1384 | 1.7058 | 0.5652 |
| 0.9342 | 9.0 | 1557 | 1.6644 | 0.5759 |
| 0.9008 | 10.0 | 1730 | 1.6572 | 0.5802 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.11.0+cu113
- Datasets 2.6.1
- Tokenizers 0.12.1
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.