metadata
tags:
- generated_from_trainer
datasets:
- common_voice_13_0
metrics:
- wer
model-index:
- name: URDU-ASR
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_13_0
type: common_voice_13_0
config: ur
split: test
args: ur
metrics:
- name: Wer
type: wer
value: 0.4850090912607838
URDU-ASR
This model was trained from scratch on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6352
- Wer: 0.4850
- Cer: 0.2045
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=(0.9,0.99) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
---|---|---|---|---|---|
2.2192 | 1.0 | 341 | 0.6603 | 0.5302 | 0.2229 |
0.3189 | 2.0 | 683 | 0.6316 | 0.5287 | 0.2295 |
0.2507 | 3.0 | 1024 | 0.6513 | 0.5032 | 0.2141 |
0.2076 | 4.0 | 1366 | 0.6459 | 0.5038 | 0.2131 |
0.1711 | 4.99 | 1705 | 0.6352 | 0.4850 | 0.2045 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1