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: inf
- Wer: 0.8094
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 |
|---|---|---|---|---|
| 3.3952 | 2.3 | 200 | inf | 0.9316 |
| 0.9044 | 4.59 | 400 | inf | 0.8832 |
| 0.5208 | 6.89 | 600 | inf | 0.8467 |
| 0.3552 | 9.19 | 800 | inf | 0.8444 |
| 0.259 | 11.49 | 1000 | inf | 0.84 |
| 0.2113 | 13.79 | 1200 | inf | 0.8321 |
| 0.1681 | 16.09 | 1400 | inf | 0.8264 |
| 0.1468 | 18.39 | 1600 | inf | 0.8281 |
| 0.1321 | 20.69 | 1800 | inf | 0.8198 |
| 0.1167 | 22.98 | 2000 | inf | 0.7958 |
| 0.1028 | 25.29 | 2200 | inf | 0.8007 |
| 0.0947 | 27.58 | 2400 | inf | 0.8035 |
| 0.0829 | 29.88 | 2600 | inf | 0.8094 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.10.0+cu113
- Datasets 1.18.3
- Tokenizers 0.13.2