<!-- 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-maltese
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - MT dataset. It achieves the following results on the evaluation set:
- Loss: 0.2005
- Wer: 0.1897
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: 100.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.2238 | 18.02 | 2000 | 0.3911 | 0.4310 |
| 0.7871 | 36.04 | 4000 | 0.2063 | 0.2309 |
| 0.6653 | 54.05 | 6000 | 0.1960 | 0.2091 |
| 0.5861 | 72.07 | 8000 | 0.1986 | 0.2000 |
| 0.5283 | 90.09 | 10000 | 0.1993 | 0.1909 |
Framework versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.1+cu102
- Datasets 1.17.1.dev0
- Tokenizers 0.11.0
