metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- fleurs
metrics:
- wer
model-index:
- name: xlsr-53-ur
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: fleurs
type: fleurs
config: ur_pk
split: test
args: ur_pk
metrics:
- name: Wer
type: wer
value: 0.3450557529714496
xlsr-53-ur
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.6860
- Wer: 0.3451
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: 6
- eval_batch_size: 6
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 12
- total_eval_batch_size: 12
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 15.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.0396 | 1.59 | 300 | 3.0179 | 1.0 |
| 0.4976 | 3.17 | 600 | 0.7037 | 0.5447 |
| 0.3062 | 4.76 | 900 | 0.5557 | 0.4036 |
| 0.2287 | 6.35 | 1200 | 0.5620 | 0.3935 |
| 0.2504 | 7.94 | 1500 | 0.5907 | 0.3677 |
| 0.0633 | 9.52 | 1800 | 0.6239 | 0.3773 |
| 0.0456 | 11.11 | 2100 | 0.6748 | 0.3604 |
| 0.0774 | 12.7 | 2400 | 0.6747 | 0.3552 |
| 0.058 | 14.29 | 2700 | 0.6860 | 0.3451 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2