wav2vec2-common_voice-tr-mms-demo
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the COMMON_VOICE - VI dataset. It achieves the following results on the evaluation set:
- Loss: 3.5581
- Wer: 1.0
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: 0.001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 1.79 | 100 | 3.6345 | 1.0 |
| No log | 3.57 | 200 | 3.6709 | 1.0 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.7.0
- Tokenizers 0.13.3