metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- common_voice
model-index:
- name: wav2vec2-large-xls-r-300m-tr-colab
results: []
wav2vec2-large-xls-r-300m-tr-colab
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.4029
- Wer: 0.3116
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: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.8607 | 3.67 | 400 | 0.7144 | 0.7305 |
| 0.4094 | 7.34 | 800 | 0.4222 | 0.5035 |
| 0.1958 | 11.01 | 1200 | 0.4438 | 0.4228 |
| 0.1353 | 14.68 | 1600 | 0.4536 | 0.3914 |
| 0.1062 | 18.35 | 2000 | 0.4161 | 0.3659 |
| 0.0791 | 22.02 | 2400 | 0.4192 | 0.3366 |
| 0.0635 | 25.69 | 2800 | 0.4048 | 0.3225 |
| 0.0511 | 29.36 | 3200 | 0.4029 | 0.3116 |
Framework versions
- Transformers 4.23.0
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.13.1