|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- common_voice |
|
model-index: |
|
- name: wav2vec2-large-xls-r-300m-turkish-colab_common_voice-8_6 |
|
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-xls-r-300m-turkish-colab_common_voice-8_6 |
|
|
|
This model is a fine-tuned version of [husnu/wav2vec2-large-xls-r-300m-turkish-colab_common_voice-8_5](https://huggingface.co/husnu/wav2vec2-large-xls-r-300m-turkish-colab_common_voice-8_5) on the common_voice dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3646 |
|
- Wer: 0.3478 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 6 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 0.1024 | 0.51 | 400 | 0.4030 | 0.4171 | |
|
| 0.1533 | 1.02 | 800 | 0.4733 | 0.4570 | |
|
| 0.1584 | 1.53 | 1200 | 0.4150 | 0.4371 | |
|
| 0.1538 | 2.04 | 1600 | 0.4104 | 0.4390 | |
|
| 0.1395 | 2.55 | 2000 | 0.3891 | 0.4133 | |
|
| 0.1415 | 3.07 | 2400 | 0.3877 | 0.4015 | |
|
| 0.1261 | 3.58 | 2800 | 0.3685 | 0.3899 | |
|
| 0.1149 | 4.09 | 3200 | 0.3791 | 0.3881 | |
|
| 0.1003 | 4.6 | 3600 | 0.3642 | 0.3626 | |
|
| 0.0934 | 5.11 | 4000 | 0.3755 | 0.3516 | |
|
| 0.0805 | 5.62 | 4400 | 0.3646 | 0.3478 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.11.3 |
|
- Pytorch 1.10.0+cu113 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.10.3 |
|
|