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_Prod14
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: 0.9997695427728613
name: Wer
wav2vec2-xlsr-53-CV-demo-google-colab-Ezra_William_Prod14
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: 1.8240
- Wer: 0.9998
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: 0.003
- 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: 12
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.8908 | 1.0 | 556 | 2.8658 | 1.0 |
| 2.8733 | 2.0 | 1112 | 2.8600 | 1.0 |
| 2.6756 | 3.0 | 1668 | 2.5449 | 1.0000 |
| 2.2847 | 4.0 | 2224 | 2.1842 | 1.0 |
| 2.2086 | 5.0 | 2780 | 2.0814 | 0.9999 |
| 2.1121 | 6.0 | 3336 | 2.0101 | 1.0 |
| 2.0778 | 7.0 | 3892 | 1.9459 | 1.0 |
| 1.9959 | 8.0 | 4448 | 1.9099 | 0.9999 |
| 1.981 | 9.0 | 5004 | 1.8806 | 0.9999 |
| 1.9512 | 10.0 | 5560 | 1.8475 | 0.9999 |
| 1.9468 | 11.0 | 6116 | 1.8366 | 0.9998 |
| 1.9164 | 12.0 | 6672 | 1.8240 | 0.9998 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2