|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: facebook/wav2vec2-xls-r-300m |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- common_voice_17_0 |
|
|
metrics: |
|
|
- wer |
|
|
model-index: |
|
|
- name: result_data-1 |
|
|
results: |
|
|
- task: |
|
|
name: Automatic Speech Recognition |
|
|
type: automatic-speech-recognition |
|
|
dataset: |
|
|
name: common_voice_17_0 |
|
|
type: common_voice_17_0 |
|
|
config: uk |
|
|
split: test |
|
|
args: uk |
|
|
metrics: |
|
|
- name: Wer |
|
|
type: wer |
|
|
value: 0.36512878573450325 |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# result_data-1 |
|
|
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_17_0 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.2220 |
|
|
- Wer: 0.3651 |
|
|
- Cer: 0.1691 |
|
|
|
|
|
## 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: 6.532628754904162e-05 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 2 |
|
|
- total_train_batch_size: 32 |
|
|
- total_eval_batch_size: 32 |
|
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 206 |
|
|
- num_epochs: 7.0 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | |
|
|
|:-------------:|:------:|:----:|:---------------:|:------:|:------:| |
|
|
| 0.6324 | 0.9099 | 1000 | 0.5004 | 0.6083 | 0.2381 | |
|
|
| 0.3497 | 1.8198 | 2000 | 0.3087 | 0.4650 | 0.1965 | |
|
|
| 0.2642 | 2.7298 | 3000 | 0.2636 | 0.4249 | 0.1841 | |
|
|
| 0.2328 | 3.6397 | 4000 | 0.2431 | 0.3960 | 0.1789 | |
|
|
| 0.1933 | 4.5496 | 5000 | 0.2289 | 0.3773 | 0.1732 | |
|
|
| 0.1783 | 5.4595 | 6000 | 0.2300 | 0.3728 | 0.1711 | |
|
|
| 0.1617 | 6.3694 | 7000 | 0.2233 | 0.3637 | 0.1700 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.49.0 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.3.2 |
|
|
- Tokenizers 0.21.0 |
|
|
|
