<!-- 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-urdu-common_voice_8_0
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 1.3860
- Wer: 0.7546
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 14
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.5253 | 1.27 | 32 | 1.3860 | 0.7546 |
0.524 | 2.55 | 64 | 1.3860 | 0.7546 |
0.5197 | 3.82 | 96 | 1.3860 | 0.7546 |
0.523 | 5.12 | 128 | 1.3860 | 0.7546 |
0.5224 | 6.39 | 160 | 1.3860 | 0.7546 |
0.5332 | 7.67 | 192 | 1.3860 | 0.7546 |
0.5227 | 8.94 | 224 | 1.3860 | 0.7546 |
0.5272 | 10.24 | 256 | 1.3860 | 0.7546 |
0.5294 | 11.51 | 288 | 1.3860 | 0.7546 |
0.5146 | 12.78 | 320 | 1.3860 | 0.7546 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.12.1