|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: wav2vec2-large-xlsr-53_toy_train_data |
|
|
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-xlsr-53_toy_train_data |
|
|
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.6357 |
|
|
- Wer: 0.5496 |
|
|
|
|
|
## 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 |
|
|
- 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: 1000 |
|
|
- num_epochs: 20 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
|
| 3.6073 | 2.1 | 250 | 3.5111 | 1.0 | |
|
|
| 3.0828 | 4.2 | 500 | 3.5133 | 1.0 | |
|
|
| 1.9969 | 6.3 | 750 | 1.3924 | 0.9577 | |
|
|
| 0.9279 | 8.4 | 1000 | 0.8378 | 0.7243 | |
|
|
| 0.6692 | 10.5 | 1250 | 0.7367 | 0.6394 | |
|
|
| 0.5273 | 12.6 | 1500 | 0.6703 | 0.5907 | |
|
|
| 0.4314 | 14.7 | 1750 | 0.6594 | 0.5718 | |
|
|
| 0.3809 | 16.8 | 2000 | 0.6138 | 0.5559 | |
|
|
| 0.3934 | 18.9 | 2250 | 0.6357 | 0.5496 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.17.0 |
|
|
- Pytorch 1.11.0+cu102 |
|
|
- Datasets 2.0.0 |
|
|
- Tokenizers 0.11.6 |
|
|
|
