<!-- 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-en-cy-ccv-btb-2306
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the PYTHON/CUSTOM_COMMON_VOICE.PY,TECHIAITH/BANC-TRAWSGRIFIADAU-BANGOR - CY dataset. It achieves the following results on the evaluation set:
- Loss: inf
- Wer: 0.2585
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 |
|---|---|---|---|---|
| 5.4249 | 0.15 | 400 | inf | 0.9986 |
| 0.9082 | 0.3 | 800 | inf | 0.5231 |
| 0.4885 | 0.45 | 1200 | inf | 0.4386 |
| 0.4237 | 0.6 | 1600 | inf | 0.4156 |
| 0.3793 | 0.75 | 2000 | inf | 0.3682 |
| 0.3503 | 0.9 | 2400 | inf | 0.3256 |
| 0.3133 | 1.06 | 2800 | inf | 0.3138 |
| 0.2693 | 1.21 | 3200 | inf | 0.3030 |
| 0.2616 | 1.36 | 3600 | inf | 0.2887 |
| 0.2479 | 1.51 | 4000 | inf | 0.2817 |
| 0.237 | 1.66 | 4400 | inf | 0.2687 |
| 0.229 | 1.81 | 4800 | inf | 0.2603 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.0
- Tokenizers 0.13.3
