|
--- |
|
license: apache-2.0 |
|
base_model: facebook/hubert-large-ls960-ft |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: mascir_fr_hubert_version1000 |
|
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. --> |
|
|
|
# mascir_fr_hubert_version1000 |
|
|
|
This model is a fine-tuned version of [facebook/hubert-large-ls960-ft](https://huggingface.co./facebook/hubert-large-ls960-ft) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0469 |
|
- Wer: 0.5322 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1000 |
|
- num_epochs: 100 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:| |
|
| No log | 2.0 | 250 | 3.0909 | 1.0 | |
|
| 5.0589 | 4.0 | 500 | 2.9060 | 1.0 | |
|
| 5.0589 | 6.0 | 750 | 1.3938 | 0.9789 | |
|
| 1.8801 | 8.0 | 1000 | 0.9636 | 0.8422 | |
|
| 1.8801 | 10.0 | 1250 | 0.8361 | 0.7644 | |
|
| 0.8006 | 12.0 | 1500 | 0.8474 | 0.7444 | |
|
| 0.8006 | 14.0 | 1750 | 0.8360 | 0.7078 | |
|
| 0.5307 | 16.0 | 2000 | 0.8514 | 0.6944 | |
|
| 0.5307 | 18.0 | 2250 | 0.8770 | 0.6544 | |
|
| 0.3998 | 20.0 | 2500 | 0.8200 | 0.65 | |
|
| 0.3998 | 22.0 | 2750 | 0.8362 | 0.63 | |
|
| 0.3281 | 24.0 | 3000 | 0.8933 | 0.6144 | |
|
| 0.3281 | 26.0 | 3250 | 0.9355 | 0.62 | |
|
| 0.262 | 28.0 | 3500 | 0.9134 | 0.6222 | |
|
| 0.262 | 30.0 | 3750 | 0.9302 | 0.5989 | |
|
| 0.2256 | 32.0 | 4000 | 0.9307 | 0.5856 | |
|
| 0.2256 | 34.0 | 4250 | 0.9078 | 0.6011 | |
|
| 0.2011 | 36.0 | 4500 | 0.9647 | 0.5822 | |
|
| 0.2011 | 38.0 | 4750 | 0.9252 | 0.5844 | |
|
| 0.1819 | 40.0 | 5000 | 0.9917 | 0.5711 | |
|
| 0.1819 | 42.0 | 5250 | 0.9577 | 0.5678 | |
|
| 0.1706 | 44.0 | 5500 | 1.0094 | 0.5722 | |
|
| 0.1706 | 46.0 | 5750 | 0.9774 | 0.5722 | |
|
| 0.1504 | 48.0 | 6000 | 0.9702 | 0.5456 | |
|
| 0.1504 | 50.0 | 6250 | 0.9575 | 0.5756 | |
|
| 0.1509 | 52.0 | 6500 | 0.9855 | 0.5644 | |
|
| 0.1509 | 54.0 | 6750 | 0.9429 | 0.5411 | |
|
| 0.1292 | 56.0 | 7000 | 1.0471 | 0.5644 | |
|
| 0.1292 | 58.0 | 7250 | 1.0106 | 0.5589 | |
|
| 0.1217 | 60.0 | 7500 | 1.0118 | 0.5544 | |
|
| 0.1217 | 62.0 | 7750 | 1.0415 | 0.5478 | |
|
| 0.1187 | 64.0 | 8000 | 1.0047 | 0.5489 | |
|
| 0.1187 | 66.0 | 8250 | 1.0700 | 0.5644 | |
|
| 0.1075 | 68.0 | 8500 | 1.0357 | 0.5444 | |
|
| 0.1075 | 70.0 | 8750 | 0.9647 | 0.5444 | |
|
| 0.1009 | 72.0 | 9000 | 1.0392 | 0.5489 | |
|
| 0.1009 | 74.0 | 9250 | 1.0569 | 0.5433 | |
|
| 0.0997 | 76.0 | 9500 | 1.0266 | 0.5456 | |
|
| 0.0997 | 78.0 | 9750 | 1.0328 | 0.54 | |
|
| 0.101 | 80.0 | 10000 | 1.0338 | 0.5522 | |
|
| 0.101 | 82.0 | 10250 | 1.0422 | 0.5511 | |
|
| 0.088 | 84.0 | 10500 | 1.0233 | 0.55 | |
|
| 0.088 | 86.0 | 10750 | 1.0446 | 0.5522 | |
|
| 0.0922 | 88.0 | 11000 | 1.0558 | 0.5467 | |
|
| 0.0922 | 90.0 | 11250 | 1.0405 | 0.5433 | |
|
| 0.0863 | 92.0 | 11500 | 1.0336 | 0.5322 | |
|
| 0.0863 | 94.0 | 11750 | 1.0575 | 0.5356 | |
|
| 0.0845 | 96.0 | 12000 | 1.0449 | 0.5378 | |
|
| 0.0845 | 98.0 | 12250 | 1.0482 | 0.5344 | |
|
| 0.0818 | 100.0 | 12500 | 1.0469 | 0.5322 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.3 |
|
- Tokenizers 0.13.3 |
|
|