xlsr-53-bemba-15hrs
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2789
- Wer: 0.3751
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 400
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.4138 | 0.71 | 400 | 0.4965 | 0.7239 |
| 0.5685 | 1.43 | 800 | 0.2939 | 0.4839 |
| 0.4471 | 2.15 | 1200 | 0.2728 | 0.4467 |
| 0.3579 | 2.86 | 1600 | 0.2397 | 0.3965 |
| 0.3087 | 3.58 | 2000 | 0.2427 | 0.4015 |
| 0.2702 | 4.29 | 2400 | 0.2539 | 0.4112 |
| 0.2406 | 5.01 | 2800 | 0.2376 | 0.3885 |
| 0.2015 | 5.72 | 3200 | 0.2492 | 0.3844 |
| 0.1759 | 6.44 | 3600 | 0.2562 | 0.3768 |
| 0.1572 | 7.16 | 4000 | 0.2789 | 0.3751 |
Framework versions
- Transformers 4.19.0.dev0
- Pytorch 1.10.0+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1
- Downloads last month
- 6
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.