---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-xls-r-tf-left-right-shuru
  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-xls-r-tf-left-right-shuru

This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0921
- Wer: 1.2628

## 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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 100
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 6.5528        | 23.81 | 500  | 0.5509          | 1.9487 |
| 0.2926        | 47.62 | 1000 | 0.1306          | 1.2756 |
| 0.1171        | 71.43 | 1500 | 0.1189          | 1.2628 |
| 0.0681        | 95.24 | 2000 | 0.0921          | 1.2628 |


### Framework versions

- Transformers 4.11.3
- Pytorch 1.10.0+cu111
- Datasets 1.13.3
- Tokenizers 0.10.3