metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: ft_wav2vec2_base_six_1000
results: []
ft_wav2vec2_base_six_1000
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4818
- Wer: 40.2628
- Cer: 18.6678
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 3.2787 | 22.73 | 1000 | 1.1585 | 59.3958 | 25.8494 |
| 0.4164 | 45.45 | 2000 | 1.2611 | 44.7175 | 20.5846 |
| 0.144 | 68.18 | 3000 | 1.3470 | 42.6865 | 19.8831 |
| 0.0774 | 90.91 | 4000 | 1.4210 | 41.7307 | 19.1922 |
| 0.05 | 113.64 | 5000 | 1.4818 | 40.2628 | 18.6678 |
Framework versions
- Transformers 4.39.3
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.15.2