metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: 1-epochs12.0-char-based-freeze_cnn-dropout0.1
results: []
1-epochs12.0-char-based-freeze_cnn-dropout0.1
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Wer: 1.0
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: 2e-05
- train_batch_size: 10
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 40
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 12.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.6685 | 1.03 | 2500 | 4.0882 | 1.0 |
| 3.6718 | 2.06 | 5000 | 4.0882 | 1.0 |
| 3.6684 | 3.1 | 7500 | 4.0882 | 1.0 |
| 0.0 | 4.13 | 10000 | nan | 1.0 |
| 0.0 | 5.16 | 12500 | nan | 1.0 |
| 0.0 | 6.19 | 15000 | nan | 1.0 |
| 0.0 | 7.22 | 17500 | nan | 1.0 |
| 0.0 | 8.25 | 20000 | nan | 1.0 |
| 0.0 | 9.29 | 22500 | nan | 1.0 |
| 0.0 | 10.32 | 25000 | nan | 1.0 |
| 0.0 | 11.35 | 27500 | nan | 1.0 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.14.1