<!-- 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-TAMIL-colab
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 1.3785
- Wer: 0.9399
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.0959 | 9.99 | 400 | 2.2197 | 1.0 |
| 0.8365 | 19.99 | 800 | 1.3999 | 0.9362 |
| 0.2329 | 29.99 | 1200 | 1.3785 | 0.9399 |
Framework versions
- Transformers 4.25.0
- Pytorch 1.10.0+cu113
- Datasets 1.18.3
- Tokenizers 0.13.3
