wav2vec2-large-xls-r-300m-turkish-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: 0.7331
- Wer: 0.7459
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.0262 | 3.67 | 400 | 0.7331 | 0.7459 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 1.18.3
- Tokenizers 0.13.3
- Downloads last month
- 5
Model tree for SyedAunZaidi/wav2vec2-large-xls-r-300m-turkish-colab
Base model
facebook/wav2vec2-xls-r-300mDataset used to train SyedAunZaidi/wav2vec2-large-xls-r-300m-turkish-colab
Evaluation results
- Wer on common_voicetest set self-reported0.746