metadata
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-base-timit-demo-google-colab
results: []
wav2vec2-base-timit-demo-google-colab
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6101
- Wer: 0.4467
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: 8
- 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: 1000
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 8.1339 | 3.01 | 500 | 3.1361 | 1.0 |
| 3.0216 | 6.02 | 1000 | 2.9545 | 1.0 |
| 1.7429 | 9.04 | 1500 | 0.7389 | 0.6513 |
| 0.7297 | 12.05 | 2000 | 0.5833 | 0.5363 |
| 0.5267 | 15.06 | 2500 | 0.5673 | 0.4910 |
| 0.3983 | 18.07 | 3000 | 0.5837 | 0.4715 |
| 0.333 | 21.08 | 3500 | 0.6013 | 0.4625 |
| 0.2918 | 24.1 | 4000 | 0.6154 | 0.4526 |
| 0.2635 | 27.11 | 4500 | 0.6101 | 0.4467 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2