|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-xls-r-1b |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: wav2vec2-1b-Elderly |
|
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. --> |
|
|
|
# wav2vec2-1b-Elderly |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4157 |
|
- Cer: 11.1137 |
|
|
|
## 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: 1 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 50 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Cer | |
|
|:-------------:|:------:|:----:|:---------------:|:-------:| |
|
| 8.645 | 0.2580 | 200 | 2.2625 | 43.7735 | |
|
| 1.4937 | 0.5161 | 400 | 1.2311 | 27.9488 | |
|
| 1.0981 | 0.7741 | 600 | 0.9801 | 23.6020 | |
|
| 0.898 | 1.0322 | 800 | 0.8050 | 20.0658 | |
|
| 0.7284 | 1.2902 | 1000 | 0.7320 | 18.3447 | |
|
| 0.6644 | 1.5483 | 1200 | 0.6092 | 15.7484 | |
|
| 0.592 | 1.8063 | 1400 | 0.5996 | 15.8893 | |
|
| 0.4926 | 2.0643 | 1600 | 0.5654 | 14.6147 | |
|
| 0.4054 | 2.3224 | 1800 | 0.4774 | 12.5822 | |
|
| 0.3902 | 2.5804 | 2000 | 0.4446 | 11.9772 | |
|
| 0.361 | 2.8385 | 2200 | 0.4157 | 11.1137 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.2 |
|
- Pytorch 2.3.1.post100 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.20.1 |
|
|
