<!-- 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-xls-r-300m-romanian
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - RO dataset. It achieves the following results on the evaluation set:
- Loss: 0.1167
- Wer: 0.1421
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: 7e-05
- train_batch_size: 32
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- num_epochs: 50.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1973 | 8.89 | 2000 | 0.4481 | 0.4849 |
| 0.6005 | 17.78 | 4000 | 0.1420 | 0.1777 |
| 0.5248 | 26.67 | 6000 | 0.1303 | 0.1651 |
| 0.4871 | 35.56 | 8000 | 0.1207 | 0.1523 |
| 0.4428 | 44.44 | 10000 | 0.1143 | 0.1425 |
Framework versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.1+cu102
- Datasets 1.17.1.dev0
- Tokenizers 0.11.0
