---
license: apache-2.0
tags:
- generated_from_trainer
base_model: facebook/wav2vec2-large-xlsr-53
datasets:
- xtreme_s
metrics:
- wer
model-index:
- name: wav2vec2-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod8
  results:
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: xtreme_s
      type: xtreme_s
      config: fleurs.id_id
      split: test
      args: fleurs.id_id
    metrics:
    - type: wer
      value: 0.42321508756174225
      name: Wer
---

<!-- 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-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod8

This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the xtreme_s dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8564
- Wer: 0.4232

## 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: 0.001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 600
- num_epochs: 180
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 4.801         | 30.77  | 300  | 2.8357          | 1.0    |
| 1.041         | 61.54  | 600  | 0.8673          | 0.5433 |
| 0.1141        | 92.31  | 900  | 0.8976          | 0.4801 |
| 0.0568        | 123.08 | 1200 | 0.8556          | 0.4427 |
| 0.035         | 153.85 | 1500 | 0.8564          | 0.4232 |


### Framework versions

- Transformers 4.39.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2