---
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-1b
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-1b-Y
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# wav2vec2-1b-Y

This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9820
- Cer: 24.1248

## 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: 8
- 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: 50
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Cer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 9.8741        | 0.2580 | 200  | 2.9382          | 58.9579 |
| 1.6995        | 0.5161 | 400  | 2.0333          | 45.6238 |
| 1.151         | 0.7741 | 600  | 1.7032          | 39.6734 |
| 0.9663        | 1.0322 | 800  | 1.2993          | 31.3675 |
| 0.8027        | 1.2902 | 1000 | 1.2846          | 33.0768 |
| 0.7227        | 1.5483 | 1200 | 1.1823          | 28.6419 |
| 0.6516        | 1.8063 | 1400 | 1.2823          | 32.2838 |
| 0.6087        | 2.0643 | 1600 | 1.2643          | 31.0209 |
| 0.5242        | 2.3224 | 1800 | 1.2452          | 30.3865 |
| 0.4763        | 2.5804 | 2000 | 1.1365          | 28.0839 |
| 0.4611        | 2.8385 | 2200 | 1.0796          | 26.5742 |
| 0.4103        | 3.0965 | 2400 | 1.1832          | 29.3527 |
| 0.3289        | 3.3546 | 2600 | 1.0230          | 25.0705 |
| 0.31          | 3.6126 | 2800 | 0.9800          | 24.8708 |
| 0.2995        | 3.8707 | 3000 | 0.9924          | 25.1880 |
| 0.2516        | 4.1287 | 3200 | 1.0370          | 25.2173 |
| 0.227         | 4.3867 | 3400 | 1.0256          | 24.8531 |
| 0.2251        | 4.6448 | 3600 | 0.9982          | 24.1424 |
| 0.2251        | 4.9028 | 3800 | 0.9820          | 24.1248 |


### Framework versions

- Transformers 4.45.2
- Pytorch 2.3.1.post100
- Datasets 2.19.1
- Tokenizers 0.20.1