---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- common_voice
model-index:
- name: Wav2Vec2_xls_r_300m_hi_cv7
  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_300m_hi_cv7

This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6567
- Wer: 0.6273
- Cer: 0.2093

## 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: 32
- 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: 100
- num_epochs: 35
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
| 5.6969        | 9.52  | 400  | 3.3092          | 1.0    | 0.9800 |
| 1.7721        | 19.05 | 800  | 0.7769          | 0.7045 | 0.2367 |
| 0.6384        | 28.57 | 1200 | 0.6567          | 0.6273 | 0.2093 |


### Framework versions

- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu102
- Datasets 1.18.3
- Tokenizers 0.11.0