|
--- |
|
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-bem-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-bem-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: 0.1638 |
|
- Wer: 0.3223 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 200 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 2.2095 | 1.03 | 200 | 0.2066 | 0.3850 | |
|
| 0.4028 | 2.06 | 400 | 0.1861 | 0.3539 | |
|
| 0.3751 | 3.09 | 600 | 0.1781 | 0.3417 | |
|
| 0.3631 | 4.12 | 800 | 0.1739 | 0.3392 | |
|
| 0.3481 | 5.15 | 1000 | 0.1688 | 0.3340 | |
|
| 0.3391 | 6.19 | 1200 | 0.1690 | 0.3319 | |
|
| 0.3301 | 7.22 | 1400 | 0.1654 | 0.3285 | |
|
| 0.3237 | 8.25 | 1600 | 0.1667 | 0.3262 | |
|
| 0.3186 | 9.28 | 1800 | 0.1638 | 0.3223 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0.dev0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.13.3 |
|
|
