hello_world
This model is a fine-tuned version of tugstugi/wav2vec2-large-xlsr-53-mongolian on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.8235
- Wer: 0.4679
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: 30
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
2.1725 | 6.78 | 400 | 0.8343 | 0.5449 |
0.1406 | 13.56 | 800 | 0.8587 | 0.5158 |
0.1013 | 20.34 | 1200 | 0.8260 | 0.4990 |
0.0701 | 27.12 | 1600 | 0.8235 | 0.4679 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 0
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.