<!-- 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-large-xls-r-300m-hsb
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.8368
- Wer: 0.5606
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: 50
- num_epochs: 75
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
4.4088 | 6.45 | 200 | 2.9819 | 0.9796 |
1.0892 | 12.9 | 400 | 0.9004 | 0.8218 |
0.1669 | 19.35 | 600 | 0.9470 | 0.7559 |
0.0915 | 25.81 | 800 | 0.8776 | 0.6828 |
0.0641 | 32.26 | 1000 | 0.8835 | 0.6579 |
0.053 | 38.71 | 1200 | 0.8653 | 0.6307 |
0.0378 | 45.16 | 1400 | 0.8675 | 0.6155 |
0.0289 | 51.61 | 1600 | 0.8349 | 0.5906 |
0.0238 | 58.06 | 1800 | 0.8459 | 0.5892 |
0.0196 | 64.52 | 2000 | 0.8308 | 0.5613 |
0.0163 | 70.97 | 2200 | 0.8368 | 0.5606 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3