metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: facebook/wav2vec2-large-xlsr-53
datasets:
- common_voice_13_0
metrics:
- wer
model-index:
- name: wav2vec2-xlsr-53-CV-demo-google-colab-Ezra_William_Prod13
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: common_voice_13_0
type: common_voice_13_0
config: id
split: test
args: id
metrics:
- type: wer
value: 0.5251659292035398
name: Wer
wav2vec2-xlsr-53-CV-demo-google-colab-Ezra_William_Prod13
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5181
- Wer: 0.5252
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 9
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.7243 | 1.0 | 556 | 2.9426 | 1.0 |
| 2.9083 | 2.0 | 1112 | 2.8444 | 1.0 |
| 2.7357 | 3.0 | 1668 | 1.2851 | 0.9653 |
| 1.5755 | 4.0 | 2224 | 0.7428 | 0.7008 |
| 1.0547 | 5.0 | 2780 | 0.6150 | 0.6204 |
| 0.908 | 6.0 | 3336 | 0.5685 | 0.5691 |
| 0.827 | 7.0 | 3892 | 0.5384 | 0.5444 |
| 0.775 | 8.0 | 4448 | 0.5243 | 0.5277 |
| 0.7225 | 9.0 | 5004 | 0.5181 | 0.5252 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2