|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- common_voice_8_0 |
|
model-index: |
|
- name: xls-r_cv_ur |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# xls-r_cv_ur |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_8_0 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7817 |
|
- Wer: 0.4186 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1000 |
|
- num_epochs: 30 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 6.3952 | 3.25 | 1000 | 3.0061 | 1.0 | |
|
| 1.6018 | 6.49 | 2000 | 0.8703 | 0.5862 | |
|
| 0.7295 | 9.74 | 3000 | 0.7436 | 0.5089 | |
|
| 0.5353 | 12.99 | 4000 | 0.7170 | 0.4793 | |
|
| 0.4255 | 16.23 | 5000 | 0.7636 | 0.4567 | |
|
| 0.3598 | 19.48 | 6000 | 0.7808 | 0.4523 | |
|
| 0.3231 | 22.73 | 7000 | 0.7663 | 0.4437 | |
|
| 0.2851 | 25.97 | 8000 | 0.7699 | 0.4308 | |
|
| 0.2669 | 29.22 | 9000 | 0.7817 | 0.4186 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.21.0 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.12.1 |
|
|
