|
|
--- |
|
|
license: cc-by-nc-4.0 |
|
|
base_model: facebook/mms-1b-all |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- wer |
|
|
model-index: |
|
|
- name: wav2vec2-large-mms-1b-bemba-colab |
|
|
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-large-mms-1b-bemba-colab |
|
|
|
|
|
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1663 |
|
|
- Wer: 0.3303 |
|
|
|
|
|
## 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: 0.001 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- 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: 100 |
|
|
- num_epochs: 15 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
|
| 2.6643 | 0.26 | 200 | 0.2147 | 0.3900 | |
|
|
| 0.4271 | 0.52 | 400 | 0.1996 | 0.3634 | |
|
|
| 0.4004 | 0.77 | 600 | 0.1911 | 0.3595 | |
|
|
| 0.3789 | 1.03 | 800 | 0.1905 | 0.3544 | |
|
|
| 0.3707 | 1.29 | 1000 | 0.1821 | 0.3461 | |
|
|
| 0.3811 | 1.55 | 1200 | 0.1815 | 0.3586 | |
|
|
| 0.3662 | 1.8 | 1400 | 0.1811 | 0.3433 | |
|
|
| 0.3627 | 2.06 | 1600 | 0.1814 | 0.3443 | |
|
|
| 0.3529 | 2.32 | 1800 | 0.1807 | 0.3375 | |
|
|
| 0.3466 | 2.58 | 2000 | 0.1758 | 0.3299 | |
|
|
| 0.3481 | 2.84 | 2200 | 0.1781 | 0.3408 | |
|
|
| 0.3446 | 3.09 | 2400 | 0.1761 | 0.3316 | |
|
|
| 0.3379 | 3.35 | 2600 | 0.1702 | 0.3305 | |
|
|
| 0.3371 | 3.61 | 2800 | 0.1668 | 0.3258 | |
|
|
| 0.3326 | 3.87 | 3000 | 0.1661 | 0.3212 | |
|
|
| 0.3297 | 4.12 | 3200 | 0.1706 | 0.3358 | |
|
|
| 0.3267 | 4.38 | 3400 | 0.1707 | 0.3322 | |
|
|
| 0.3328 | 4.64 | 3600 | 0.1663 | 0.3303 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.31.0.dev0 |
|
|
- Pytorch 2.0.1+cu118 |
|
|
- Datasets 2.13.1 |
|
|
- Tokenizers 0.13.3 |
|
|
|
