---
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: 1-epochs6.0-char-based-freeze_cnn-dropout0.1
  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. -->

# 1-epochs6.0-char-based-freeze_cnn-dropout0.1

This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co./facebook/wav2vec2-xls-r-300m) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7833
- Wer: 0.4843

## 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: 2e-05
- train_batch_size: 10
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 40
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 6.0

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Wer    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 3.4067        | 0.57  | 2500  | 3.5770          | 1.0    |
| 2.3866        | 1.14  | 5000  | 2.1913          | 1.0236 |
| 1.2369        | 1.7   | 7500  | 1.0121          | 0.6844 |
| 1.3609        | 2.27  | 10000 | 0.9048          | 0.5847 |
| 1.0586        | 2.84  | 12500 | 0.8494          | 0.5447 |
| 0.7728        | 3.41  | 15000 | 0.8188          | 0.5185 |
| 1.0428        | 3.98  | 17500 | 0.7845          | 0.4961 |
| 0.8995        | 4.55  | 20000 | 0.7846          | 0.4884 |
| 0.7284        | 5.11  | 22500 | 0.7877          | 0.4866 |
| 0.7733        | 5.68  | 25000 | 0.7833          | 0.4843 |


### Framework versions

- Transformers 4.34.0
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.14.1