metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- common_voice
metrics:
- wer
model-index:
- name: asr_skripsi_colab_common_voice
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice
type: common_voice
config: id
split: test
args: id
metrics:
- name: Wer
type: wer
value: 0.36856617647058826
asr_skripsi_colab_common_voice
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.3839
- Wer: 0.3686
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: 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 |
|---|---|---|---|---|
| 4.4354 | 3.64 | 400 | 1.9595 | 1.0 |
| 0.7227 | 7.27 | 800 | 0.4532 | 0.5039 |
| 0.3293 | 10.91 | 1200 | 0.4277 | 0.4425 |
| 0.2298 | 14.55 | 1600 | 0.3947 | 0.4182 |
| 0.1789 | 18.18 | 2000 | 0.3960 | 0.4009 |
| 0.1496 | 21.82 | 2400 | 0.3793 | 0.3848 |
| 0.122 | 25.45 | 2800 | 0.3794 | 0.3795 |
| 0.1056 | 29.09 | 3200 | 0.3839 | 0.3686 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2