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: 4.0959
- Wer: 1.0406
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 |
|---|---|---|---|---|
| 3.6321 | 2.04 | 200 | 2.3063 | 0.9872 |
| 1.8629 | 4.08 | 400 | 2.4143 | 0.9926 |
| 1.3881 | 6.12 | 600 | 2.5862 | 0.9795 |
| 1.0565 | 8.16 | 800 | 2.6708 | 1.0191 |
| 0.7681 | 10.2 | 1000 | 3.1001 | 0.9992 |
| 0.5867 | 12.24 | 1200 | 3.4503 | 1.0228 |
| 0.4289 | 14.29 | 1400 | 3.5382 | 1.0165 |
| 0.3618 | 16.33 | 1600 | 3.5116 | 0.9835 |
| 0.3229 | 18.37 | 1800 | 3.6524 | 1.0093 |
| 0.2483 | 20.41 | 2000 | 3.6222 | 1.0319 |
| 0.2215 | 22.45 | 2200 | 3.9824 | 1.0414 |
| 0.1833 | 24.49 | 2400 | 3.9272 | 1.0393 |
| 0.1706 | 26.53 | 2600 | 3.9290 | 1.0425 |
| 0.1463 | 28.57 | 2800 | 4.0959 | 1.0406 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.10.0+cu113
- Datasets 1.18.3
- Tokenizers 0.13.2