<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
wav2vec2-common_voice-tr-demo
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the COMMON_VOICE - TR dataset. It achieves the following results on the evaluation set:
- Loss: 0.5682
- Wer: 0.5739
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: 64
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 15.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 3.69 | 100 | 3.5365 | 1.0 |
| No log | 7.4 | 200 | 2.9341 | 0.9999 |
| No log | 11.11 | 300 | 0.6994 | 0.6841 |
| No log | 14.8 | 400 | 0.5623 | 0.5792 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.11.0+cu113
- Datasets 2.6.1
- Tokenizers 0.12.1
