metadata
language:
- gn
license: apache-2.0
base_model: glob-asr/wav2vec2-large-xls-r-300m-guarani-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_1
model-index:
- name: Common Voice 16
results: []
Common Voice 16
This model is a fine-tuned version of glob-asr/wav2vec2-large-xls-r-300m-guarani-small on the Common Voice 16 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3490
- Cer: 7.9739
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 16
- 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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.4171 | 1.0152 | 100 | 0.3798 | 8.5448 |
| 0.3367 | 2.0305 | 200 | 0.3633 | 8.4451 |
| 0.2914 | 3.0457 | 300 | 0.3564 | 8.1279 |
| 0.261 | 4.0609 | 400 | 0.3494 | 7.9014 |
| 0.2464 | 5.0761 | 500 | 0.3490 | 7.9739 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1