xls-r-asr_xh-run8
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the asr_xh dataset. It achieves the following results:
- Wer (Validation): 53.87%
- Wer (Test): 53.71%
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: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer (Train) |
|---|---|---|---|---|
| 4.8608 | 2.55 | 400 | 1.0758 | 0.9336 |
| 0.6639 | 5.1 | 800 | 0.4369 | 0.6246 |
| 0.3031 | 7.64 | 1200 | 0.4297 | 0.5387 |
| 0.1931 | 10.19 | 1600 | 0.5037 | 0.5329 |
| 0.138 | 12.74 | 2000 | 0.4914 | 0.5549 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 6
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.