|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- common_voice |
|
model-index: |
|
- name: '' |
|
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. --> |
|
|
|
# |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the common_voice dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4191 |
|
- Wer: 0.9357 |
|
|
|
## 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: 6.5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2000 |
|
- num_epochs: 10.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 2.2416 | 0.84 | 500 | 1.2867 | 0.8875 | |
|
| 2.3089 | 1.67 | 1000 | 1.8336 | 0.9548 | |
|
| 2.3614 | 2.51 | 1500 | 1.5937 | 0.9469 | |
|
| 2.5234 | 3.35 | 2000 | 1.9765 | 0.9867 | |
|
| 2.5373 | 4.19 | 2500 | 1.9062 | 0.9916 | |
|
| 2.5703 | 5.03 | 3000 | 1.9772 | 0.9915 | |
|
| 2.4656 | 5.86 | 3500 | 1.8083 | 0.9829 | |
|
| 2.4339 | 6.7 | 4000 | 1.7548 | 0.9752 | |
|
| 2.344 | 7.54 | 4500 | 1.6146 | 0.9638 | |
|
| 2.2677 | 8.38 | 5000 | 1.5105 | 0.9499 | |
|
| 2.2074 | 9.21 | 5500 | 1.4191 | 0.9357 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.17.0.dev0 |
|
- Pytorch 1.10.2+cu102 |
|
- Datasets 1.18.2.dev0 |
|
- Tokenizers 0.11.0 |
|
|