metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: facebook/wav2vec2-xls-r-300m
datasets:
- common_voice_13_0
metrics:
- wer
model-index:
- name: wav2vec2-xlsr-53-CV-demo-google-colab-Ezra_William_Prod17
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: 0.3274336283185841
name: Wer
wav2vec2-xlsr-53-CV-demo-google-colab-Ezra_William_Prod17
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3395
- Wer: 0.3274
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: 16
- 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 |
|---|---|---|---|---|
| 2.9137 | 1.0 | 278 | 2.8202 | 1.0 |
| 0.8546 | 2.0 | 556 | 0.6314 | 0.6728 |
| 0.4738 | 3.0 | 834 | 0.4380 | 0.4837 |
| 0.3338 | 4.0 | 1112 | 0.4024 | 0.4490 |
| 0.2557 | 5.0 | 1390 | 0.3622 | 0.4295 |
| 0.1972 | 6.0 | 1668 | 0.3381 | 0.3795 |
| 0.1644 | 7.0 | 1946 | 0.3632 | 0.3706 |
| 0.1442 | 8.0 | 2224 | 0.3352 | 0.3578 |
| 0.1287 | 9.0 | 2502 | 0.3441 | 0.3496 |
| 0.1122 | 10.0 | 2780 | 0.3501 | 0.3437 |
| 0.1035 | 11.0 | 3058 | 0.3389 | 0.3322 |
| 0.0961 | 12.0 | 3336 | 0.3395 | 0.3274 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1