metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-large-xlsr-turkish-demo-colab
results: []
wav2vec2-large-xlsr-turkish-demo-colab
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4445
- Wer: 0.3395
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: 32
- 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: 1000
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.3698 | 4.0 | 500 | 1.2798 | 0.8525 |
| 0.5719 | 8.0 | 1000 | 0.4563 | 0.4530 |
| 0.2282 | 12.0 | 1500 | 0.4731 | 0.3967 |
| 0.1311 | 16.0 | 2000 | 0.4619 | 0.3725 |
| 0.0873 | 20.0 | 2500 | 0.4516 | 0.3558 |
| 0.0635 | 24.0 | 3000 | 0.4348 | 0.3517 |
| 0.0512 | 28.0 | 3500 | 0.4445 | 0.3395 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 1.18.3
- Tokenizers 0.13.3