metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-large-xls-r-300m-telugu-asr
results: []
wav2vec2-large-xls-r-300m-telugu-asr
This model is a fine-tuned version of henilp105/wav2vec2-large-xls-r-300m-telugu-asr on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2032
- Wer: 0.6921
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1347 | 4.65 | 200 | 0.8580 | 0.6825 |
| 0.2853 | 9.3 | 400 | 1.0124 | 0.7056 |
| 0.2096 | 13.95 | 600 | 1.0856 | 0.7187 |
| 0.1418 | 18.6 | 800 | 1.1826 | 0.7131 |
| 0.1016 | 23.26 | 1000 | 1.2104 | 0.7046 |
| 0.0771 | 27.91 | 1200 | 1.2032 | 0.6921 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.10.0+cu113
- Datasets 1.18.3
- Tokenizers 0.13.2