metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- common_voice
model-index:
- name: wav2vec2-large-xls-r-300m-turkish-colab_common_voice-8_5
results: []
wav2vec2-large-xls-r-300m-turkish-colab_common_voice-8_5
This model is a fine-tuned version of husnu/wav2vec2-large-xls-r-300m-turkish-colab_common_voice-8_4 on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.3439
- Wer: 0.3634
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: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.1243 | 0.51 | 400 | 0.4312 | 0.4202 |
0.1956 | 1.02 | 800 | 0.4421 | 0.4498 |
0.1816 | 1.53 | 1200 | 0.4012 | 0.4285 |
0.1548 | 2.04 | 1600 | 0.3720 | 0.3845 |
0.1171 | 2.55 | 2000 | 0.3439 | 0.3634 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu113
- Datasets 2.1.0
- Tokenizers 0.10.3