<!-- 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-bengali-v7
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: 3.2999
- Wer: 1.0
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: 4e-05
- 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: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
9.965 | 0.85 | 400 | 4.0076 | 1.0 |
3.5381 | 1.71 | 800 | 3.3463 | 1.0 |
3.3333 | 2.56 | 1200 | 3.2927 | 1.0 |
3.307 | 3.41 | 1600 | 3.3024 | 1.0 |
3.3386 | 4.26 | 2000 | 3.2984 | 1.0 |
3.3277 | 5.12 | 2400 | 3.2999 | 1.0 |
3.3145 | 5.97 | 2800 | 3.2999 | 1.0 |
3.3306 | 6.82 | 3200 | 3.2999 | 1.0 |
3.326 | 7.68 | 3600 | 3.2999 | 1.0 |
3.3143 | 8.53 | 4000 | 3.2999 | 1.0 |
3.3311 | 9.38 | 4400 | 3.2999 | 1.0 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1