metadata
license: mit
base_model: facebook/w2v-bert-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-bert-CV16-en-libri
results: []
wav2vec2-bert-CV16-en-libri
This model is a fine-tuned version of facebook/w2v-bert-2.0 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2870
- Wer: 0.2577
- Cer: 0.0659
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: 3e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- distributed_type: multi-GPU
- num_devices: 3
- gradient_accumulation_steps: 2
- total_train_batch_size: 72
- total_eval_batch_size: 36
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
---|---|---|---|---|---|
2.8812 | 0.63 | 250 | 2.8923 | 1.0 | 1.0000 |
1.2899 | 1.26 | 500 | 1.1471 | 0.7030 | 0.2563 |
0.5276 | 1.89 | 750 | 0.4687 | 0.4114 | 0.1127 |
0.3313 | 2.52 | 1000 | 0.2870 | 0.2577 | 0.0659 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0