|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- common_voice |
|
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 [indonesian-nlp/wav2vec2-luganda](https://huggingface.co/indonesian-nlp/wav2vec2-luganda) on the common_voice dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 8.8279 |
|
- Wer: 1.0123 |
|
|
|
## 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: 1e-08 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 256 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 10.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 8.1684 | 0.25 | 10 | 8.8588 | 1.0125 | |
|
| 8.1428 | 0.5 | 20 | 8.8569 | 1.0125 | |
|
| 8.1333 | 0.75 | 30 | 8.8552 | 1.0124 | |
|
| 8.7873 | 1.03 | 40 | 8.8532 | 1.0124 | |
|
| 8.1298 | 1.28 | 50 | 8.8516 | 1.0124 | |
|
| 8.1445 | 1.53 | 60 | 8.8499 | 1.0123 | |
|
| 8.1635 | 1.78 | 70 | 8.8483 | 1.0124 | |
|
| 8.7587 | 2.05 | 80 | 8.8468 | 1.0125 | |
|
| 8.1424 | 2.3 | 90 | 8.8454 | 1.0124 | |
|
| 8.1318 | 2.55 | 100 | 8.8440 | 1.0124 | |
|
| 8.1469 | 2.81 | 110 | 8.8428 | 1.0125 | |
|
| 8.7602 | 3.08 | 120 | 8.8416 | 1.0125 | |
|
| 8.1584 | 3.33 | 130 | 8.8405 | 1.0126 | |
|
| 8.142 | 3.58 | 140 | 8.8394 | 1.0126 | |
|
| 8.1285 | 3.83 | 150 | 8.8384 | 1.0124 | |
|
| 8.7756 | 4.1 | 160 | 8.8371 | 1.0124 | |
|
| 8.0991 | 4.35 | 170 | 8.8363 | 1.0125 | |
|
| 8.1442 | 4.6 | 180 | 8.8354 | 1.0124 | |
|
| 8.1294 | 4.86 | 190 | 8.8346 | 1.0124 | |
|
| 8.7276 | 5.13 | 200 | 8.8338 | 1.0125 | |
|
| 8.1439 | 5.38 | 210 | 8.8329 | 1.0124 | |
|
| 8.1115 | 5.63 | 220 | 8.8322 | 1.0124 | |
|
| 8.1501 | 5.88 | 230 | 8.8316 | 1.0125 | |
|
| 8.7143 | 6.15 | 240 | 8.8308 | 1.0124 | |
|
| 8.143 | 6.4 | 250 | 8.8302 | 1.0124 | |
|
| 8.1528 | 6.65 | 260 | 8.8300 | 1.0125 | |
|
| 8.1293 | 6.91 | 270 | 8.8297 | 1.0124 | |
|
| 8.7519 | 7.18 | 280 | 8.8293 | 1.0125 | |
|
| 8.1153 | 7.43 | 290 | 8.8289 | 1.0124 | |
|
| 8.1292 | 7.68 | 300 | 8.8288 | 1.0124 | |
|
| 8.0904 | 7.93 | 310 | 8.8284 | 1.0124 | |
|
| 8.7425 | 8.2 | 320 | 8.8283 | 1.0125 | |
|
| 8.0963 | 8.45 | 330 | 8.8281 | 1.0124 | |
|
| 8.1112 | 8.7 | 340 | 8.8281 | 1.0124 | |
|
| 8.124 | 8.96 | 350 | 8.8281 | 1.0125 | |
|
| 8.7327 | 9.23 | 360 | 8.8279 | 1.0123 | |
|
| 8.1261 | 9.48 | 370 | 8.8279 | 1.0126 | |
|
| 8.1259 | 9.73 | 380 | 8.8279 | 1.0124 | |
|
| 8.1116 | 9.98 | 390 | 8.8279 | 1.0123 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.17.0.dev0 |
|
- Pytorch 1.10.2+cu102 |
|
- Datasets 1.18.3 |
|
- Tokenizers 0.11.0 |
|
|
