metadata
license: apache-2.0
base_model: facebook/wav2vec2-conformer-rel-pos-large
tags:
- generated_from_trainer
datasets:
- common_voice_13_0
metrics:
- wer
model-index:
- name: wav2vec2-conformer-large-cv13
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_13_0
type: common_voice_13_0
config: ja
split: test[:10%]
args: ja
metrics:
- name: Wer
type: wer
value: 0.961053330382828
wav2vec2-conformer-large-cv13
This model is a fine-tuned version of facebook/wav2vec2-conformer-rel-pos-large on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 5.3295
- Wer: 0.9611
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 8.4756 | 1.0 | 715 | 5.7619 | 1.0 |
| 5.6554 | 2.0 | 1430 | 5.7260 | 1.0 |
| 5.4654 | 3.0 | 2146 | 5.5588 | 0.9993 |
| 5.421 | 4.0 | 2861 | 5.5970 | 0.9918 |
| 5.3141 | 5.0 | 3577 | 5.4359 | 0.9794 |
| 5.2603 | 6.0 | 4292 | 5.4187 | 0.9792 |
| 5.1834 | 7.0 | 5008 | 5.3865 | 0.9785 |
| 5.1195 | 8.0 | 5723 | 5.3875 | 0.9661 |
| 5.0788 | 9.0 | 6438 | 5.3399 | 0.9668 |
| 4.9988 | 9.99 | 7150 | 5.3295 | 0.9611 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0