<!-- 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-xlsr-53-ft-ccv-s99-cy
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the PYTHON/CUSTOM_COMMON_VOICE.PY - CY dataset. It achieves the following results on the evaluation set:
- Loss: 0.1025
- Wer: 0.0925
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 800
- training_steps: 5000
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
5.3854 | 0.36 | 400 | 1.0483 | 0.7906 |
0.6308 | 0.71 | 800 | 0.4050 | 0.3941 |
0.3694 | 1.07 | 1200 | 0.2283 | 0.2391 |
0.2585 | 1.43 | 1600 | 0.1821 | 0.1894 |
0.2187 | 1.78 | 2000 | 0.1530 | 0.1572 |
0.1811 | 2.14 | 2400 | 0.1452 | 0.1501 |
0.1421 | 2.5 | 2800 | 0.1273 | 0.1320 |
0.1301 | 2.85 | 3200 | 0.1208 | 0.1235 |
0.1074 | 3.21 | 3600 | 0.1131 | 0.1077 |
0.0894 | 3.57 | 4000 | 0.1093 | 0.1034 |
0.0846 | 3.93 | 4400 | 0.1013 | 0.0971 |
0.0692 | 4.28 | 4800 | 0.1020 | 0.0931 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3