|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: krishivoice |
|
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. --> |
|
|
|
# krishivoice |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6148 |
|
- Wer: 0.2809 |
|
|
|
## 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: 200 |
|
- num_epochs: 100 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-------:|:-----:|:---------------:|:------:| |
|
| 0.3768 | 9.0909 | 1000 | 0.5920 | 0.4378 | |
|
| 0.1392 | 18.1818 | 2000 | 0.5513 | 0.3537 | |
|
| 0.0823 | 27.2727 | 3000 | 0.5021 | 0.3260 | |
|
| 0.0566 | 36.3636 | 4000 | 0.5473 | 0.3163 | |
|
| 0.0886 | 45.4545 | 5000 | 0.5637 | 0.3098 | |
|
| 0.0368 | 54.5455 | 6000 | 0.5558 | 0.3004 | |
|
| 0.0264 | 63.6364 | 7000 | 0.6315 | 0.2919 | |
|
| 0.0214 | 72.7273 | 8000 | 0.5927 | 0.2902 | |
|
| 0.0124 | 81.8182 | 9000 | 0.6936 | 0.2874 | |
|
| 0.0132 | 90.9091 | 10000 | 0.6311 | 0.2858 | |
|
| 0.0094 | 100.0 | 11000 | 0.6148 | 0.2809 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
