metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- openslr
metrics:
- wer
model-index:
- name: Telugu-ASR
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: openslr
type: openslr
config: SLR66
split: train
args: SLR66
metrics:
- name: Wer
type: wer
value: 0.2884547694473777
Telugu-ASR This model is a fine-tuned version of Wav2Vec2 on the openslr dataset. It achieves the following results on the evaluation set:
- Loss: 0.2982
- Wer: 0.2885
Model description
- learning_rate: 0.0003
- 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: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.6905 | 3.84 | 400 | 0.7109 | 0.7800 |
| 0.4532 | 7.69 | 800 | 0.2972 | 0.3977 |
| 0.1957 | 11.54 | 1200 | 0.2907 | 0.3522 |
| 0.1284 | 15.38 | 1600 | 0.3117 | 0.3317 |
| 0.0979 | 19.23 | 2000 | 0.3000 | 0.3353 |
| 0.0749 | 23.08 | 2400 | 0.2823 | 0.3045 |
| 0.0584 | 26.92 | 2800 | 0.2982 | 0.2885 |