metadata
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- generated_from_trainer
datasets:
- common_voice_13_0
metrics:
- wer
model-index:
- name: XLS-R-demo-google-colab-Ezra_William_Prod_3
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_13_0
type: common_voice_13_0
config: id
split: validation
args: id
metrics:
- name: Wer
type: wer
value: 1
XLS-R-demo-google-colab-Ezra_William_Prod_3
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: 2.3315
- Wer: 1.0
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.5808 | 1.0 | 121 | 2.9812 | 1.0 |
| 2.9599 | 2.0 | 242 | 2.9396 | 1.0 |
| 2.9317 | 3.0 | 363 | 2.9082 | 1.0 |
| 2.9194 | 4.0 | 484 | 2.9076 | 1.0 |
| 2.9058 | 5.0 | 605 | 2.8958 | 1.0 |
| 2.8962 | 6.0 | 726 | 2.8816 | 1.0 |
| 2.8732 | 7.0 | 847 | 2.8341 | 1.0 |
| 2.8555 | 8.0 | 968 | 2.6998 | 1.0 |
| 2.7654 | 9.0 | 1089 | 2.4282 | 1.0 |
| 2.4844 | 10.0 | 1210 | 2.3315 | 1.0 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1