|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- evanarlian/common_voice_11_0_id_filtered |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: wav2vec2-xls-r-164m-id |
|
results: |
|
- task: |
|
name: Automatic Speech Recognition |
|
type: automatic-speech-recognition |
|
dataset: |
|
name: evanarlian/common_voice_11_0_id_filtered |
|
type: evanarlian/common_voice_11_0_id_filtered |
|
metrics: |
|
- name: Wer |
|
type: wer |
|
value: 0.2990499031454663 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# wav2vec2-xls-r-164m-id |
|
|
|
This model is a fine-tuned version of [evanarlian/wav2vec2-xls-r-164m-id](https://huggingface.co/evanarlian/wav2vec2-xls-r-164m-id) on the evanarlian/common_voice_11_0_id_filtered dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3510 |
|
- Wer: 0.2990 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 24 |
|
- eval_batch_size: 24 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.2 |
|
- num_epochs: 50.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:| |
|
| 0.089 | 1.84 | 2000 | 0.3205 | 0.3168 | |
|
| 0.0882 | 3.67 | 4000 | 0.3243 | 0.3203 | |
|
| 0.0868 | 5.51 | 6000 | 0.3272 | 0.3183 | |
|
| 0.0926 | 7.35 | 8000 | 0.3365 | 0.3209 | |
|
| 0.0943 | 9.18 | 10000 | 0.3400 | 0.3221 | |
|
| 0.0979 | 11.02 | 12000 | 0.3269 | 0.3192 | |
|
| 0.09 | 12.86 | 14000 | 0.3384 | 0.3164 | |
|
| 0.0877 | 14.69 | 16000 | 0.3284 | 0.3183 | |
|
| 0.0808 | 16.53 | 18000 | 0.3366 | 0.3189 | |
|
| 0.0835 | 18.37 | 20000 | 0.3306 | 0.3156 | |
|
| 0.08 | 20.2 | 22000 | 0.3384 | 0.3133 | |
|
| 0.0806 | 22.04 | 24000 | 0.3307 | 0.3109 | |
|
| 0.0749 | 23.88 | 26000 | 0.3493 | 0.3118 | |
|
| 0.073 | 25.71 | 28000 | 0.3479 | 0.3088 | |
|
| 0.0754 | 27.55 | 30000 | 0.3482 | 0.3109 | |
|
| 0.0697 | 29.38 | 32000 | 0.3515 | 0.3090 | |
|
| 0.07 | 31.22 | 34000 | 0.3532 | 0.3101 | |
|
| 0.0672 | 33.06 | 36000 | 0.3668 | 0.3086 | |
|
| 0.0713 | 34.89 | 38000 | 0.3560 | 0.3048 | |
|
| 0.0637 | 36.73 | 40000 | 0.3522 | 0.3028 | |
|
| 0.0695 | 38.57 | 42000 | 0.3407 | 0.3014 | |
|
| 0.0657 | 40.4 | 44000 | 0.3456 | 0.3025 | |
|
| 0.0598 | 42.24 | 46000 | 0.3498 | 0.3013 | |
|
| 0.059 | 44.08 | 48000 | 0.3563 | 0.3012 | |
|
| 0.0645 | 45.91 | 50000 | 0.3514 | 0.3002 | |
|
| 0.0595 | 47.75 | 52000 | 0.3545 | 0.3000 | |
|
| 0.064 | 49.59 | 54000 | 0.3510 | 0.2990 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.0.dev0 |
|
- Pytorch 1.13.1+cu117 |
|
- Datasets 2.9.1.dev0 |
|
- Tokenizers 0.13.2 |
|
|
