wav2vec2-common_voice-tr-demo-mini
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the MOZILLA-FOUNDATION/COMMON_VOICE_16_0 - TR dataset. It achieves the following results on the evaluation set:
- Loss: 0.9823
- Wer: 0.9383
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.5333 | 100 | 4.0238 | 1.0 |
| No log | 1.0667 | 200 | 3.2451 | 1.0 |
| No log | 1.6 | 300 | 2.9997 | 1.0 |
| No log | 2.1333 | 400 | 1.4256 | 1.0054 |
| 4.5926 | 2.6667 | 500 | 1.2465 | 0.9730 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1