|
--- |
|
license: apache-2.0 |
|
base_model: EzraWilliam/XLS-R-demo-google-colab-Ezra_William_Prod_3 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- common_voice_13_0 |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: XLS-R-demo-google-colab-Ezra_William_Prod_3 |
|
results: |
|
- task: |
|
name: Automatic Speech Recognition |
|
type: automatic-speech-recognition |
|
dataset: |
|
name: common_voice_13_0 |
|
type: common_voice_13_0 |
|
config: id |
|
split: validation |
|
args: id |
|
metrics: |
|
- name: Wer |
|
type: wer |
|
value: 0.5589213319364096 |
|
--- |
|
|
|
<!-- 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-demo-google-colab-Ezra_William_Prod_3 |
|
|
|
This model is a fine-tuned version of [EzraWilliam/XLS-R-demo-google-colab-Ezra_William_Prod_3](https://huggingface.co/EzraWilliam/XLS-R-demo-google-colab-Ezra_William_Prod_3) on the common_voice_13_0 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6384 |
|
- Wer: 0.5589 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 2.1618 | 1.0 | 121 | 1.3936 | 0.9716 | |
|
| 1.4458 | 2.0 | 242 | 0.9181 | 0.7821 | |
|
| 1.0146 | 3.0 | 363 | 0.7892 | 0.7048 | |
|
| 0.8449 | 4.0 | 484 | 0.7344 | 0.6507 | |
|
| 0.652 | 5.0 | 605 | 0.6840 | 0.6268 | |
|
| 0.593 | 6.0 | 726 | 0.6598 | 0.5980 | |
|
| 0.5549 | 7.0 | 847 | 0.6494 | 0.5817 | |
|
| 0.5206 | 8.0 | 968 | 0.6572 | 0.5759 | |
|
| 0.4958 | 9.0 | 1089 | 0.6376 | 0.5646 | |
|
| 0.4683 | 10.0 | 1210 | 0.6384 | 0.5589 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
