metadata
license: apache-2.0
base_model: facebook/wav2vec2-large
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2_large_1.1
results: []
wav2vec2_large_1.1
This model is a fine-tuned version of facebook/wav2vec2-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1063
- Wer: 1.0
- Cer: 0.9997
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: 0.001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 3.8007 | 1.12 | 700 | 3.0604 | 1.0 | 0.9997 |
| 3.3783 | 2.24 | 1400 | 3.2217 | 1.0 | 0.9997 |
| 3.2938 | 3.36 | 2100 | 3.1471 | 1.0 | 0.9997 |
| 3.2049 | 4.48 | 2800 | 3.1063 | 1.0 | 0.9997 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2