|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-xlsr-53-espeak-cv-ft |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: tamasheq-99 |
|
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. --> |
|
|
|
# tamasheq-99 |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xlsr-53-espeak-cv-ft](https://huggingface.co/facebook/wav2vec2-xlsr-53-espeak-cv-ft) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.8641 |
|
- Wer: 1.0 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 10.0753 | 2.86 | 10 | 10.1435 | 1.6667 | |
|
| 9.4458 | 5.71 | 20 | 9.0880 | 1.0 | |
|
| 8.6766 | 8.57 | 30 | 7.2508 | 1.0 | |
|
| 6.5268 | 11.43 | 40 | 4.9611 | 1.0 | |
|
| 4.9686 | 14.29 | 50 | 3.6603 | 1.0 | |
|
| 3.7601 | 17.14 | 60 | 3.2519 | 1.0 | |
|
| 3.2887 | 20.0 | 70 | 3.0620 | 1.0 | |
|
| 3.1475 | 22.86 | 80 | 2.9495 | 1.0 | |
|
| 3.0013 | 25.71 | 90 | 2.8641 | 1.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
