---
license: apache-2.0
base_model: facebook/hubert-base-ls960
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- recall
- precision
model-index:
- name: hubert-base-ls960-finetuned-common_voice
  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. -->

# hubert-base-ls960-finetuned-common_voice

This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1194
- Accuracy: 0.9925
- F1: 0.9925
- Recall: 0.9925
- Precision: 0.9926
- Mcc: 0.9906
- Auc: 0.9994

## 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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Recall | Precision | Mcc    | Auc    |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|:------:|:------:|
| 0.6461        | 0.96  | 12   | 0.4123          | 0.9725   | 0.9725 | 0.9725 | 0.9736    | 0.9659 | 0.9992 |
| 0.622         | 2.0   | 25   | 0.3858          | 0.9225   | 0.9214 | 0.9225 | 0.9354    | 0.9067 | 0.9943 |
| 0.4827        | 2.96  | 37   | 0.2750          | 0.97     | 0.9699 | 0.97   | 0.9731    | 0.9633 | 0.9988 |
| 0.3907        | 4.0   | 50   | 0.2061          | 0.98     | 0.9800 | 0.9800 | 0.9809    | 0.9752 | 0.9998 |
| 0.3212        | 4.96  | 62   | 0.1654          | 0.99     | 0.9900 | 0.9900 | 0.9902    | 0.9875 | 0.9999 |
| 0.2865        | 6.0   | 75   | 0.1355          | 0.9925   | 0.9925 | 0.9925 | 0.9926    | 0.9906 | 1.0000 |
| 0.278         | 6.96  | 87   | 0.1379          | 0.9925   | 0.9925 | 0.9925 | 0.9926    | 0.9906 | 0.9989 |
| 0.2285        | 8.0   | 100  | 0.1199          | 0.995    | 0.9950 | 0.9950 | 0.9950    | 0.9938 | 0.9993 |
| 0.1975        | 8.96  | 112  | 0.1239          | 0.99     | 0.9900 | 0.9900 | 0.9902    | 0.9875 | 0.9994 |
| 0.1949        | 9.6   | 120  | 0.1194          | 0.9925   | 0.9925 | 0.9925 | 0.9926    | 0.9906 | 0.9994 |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1