|
--- |
|
license: apache-2.0 |
|
tags: |
|
- automatic-speech-recognition |
|
- openslr_SLR66 |
|
- robust-speech-event |
|
- generated_from_trainer |
|
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 OPENSLR_SLR66 - NA dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.3845 |
|
- Wer: 0.9869 |
|
|
|
## 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-07 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 4 |
|
- 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: 300 |
|
- num_epochs: 100.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 3.5131 | 9.61 | 500 | 3.5294 | 1.0 | |
|
| 2.8596 | 19.23 | 1000 | 3.5708 | 1.0 | |
|
| 1.9055 | 28.84 | 1500 | 3.6433 | 1.0007 | |
|
| 1.4239 | 38.46 | 2000 | 3.6569 | 0.9995 | |
|
| 1.2168 | 48.08 | 2500 | 3.6079 | 0.9957 | |
|
| 1.1063 | 57.69 | 3000 | 3.5738 | 0.9925 | |
|
| 1.0404 | 67.31 | 3500 | 3.4857 | 0.9889 | |
|
| 1.001 | 76.92 | 4000 | 3.4882 | 0.9858 | |
|
| 0.982 | 86.54 | 4500 | 3.3851 | 0.9871 | |
|
| 0.9612 | 96.15 | 5000 | 3.3869 | 0.9873 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.16.0.dev0 |
|
- Pytorch 1.10.1+cu102 |
|
- Datasets 1.17.1.dev0 |
|
- Tokenizers 0.11.0 |
|
|
