---
license: cc-by-nc-4.0
base_model: facebook/mms-1b-all
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-large-mms-1b-wolof
  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-large-mms-1b-wolof

This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1481
- Wer: 0.1833

## 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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Wer    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 5.7881        | 1.0   | 875   | 0.2355          | 0.2978 |
| 0.4912        | 2.0   | 1750  | 0.2088          | 0.2670 |
| 0.4611        | 3.0   | 2625  | 0.1927          | 0.2467 |
| 0.4455        | 4.0   | 3500  | 0.1869          | 0.2339 |
| 0.4334        | 5.0   | 4375  | 0.1776          | 0.2221 |
| 0.4209        | 6.0   | 5250  | 0.1744          | 0.2150 |
| 0.4168        | 7.0   | 6125  | 0.1682          | 0.2070 |
| 0.4069        | 8.0   | 7000  | 0.1652          | 0.2054 |
| 0.3999        | 9.0   | 7875  | 0.1619          | 0.2044 |
| 0.3929        | 10.0  | 8750  | 0.1617          | 0.1996 |
| 0.3877        | 11.0  | 9625  | 0.1573          | 0.1957 |
| 0.382         | 12.0  | 10500 | 0.1557          | 0.1993 |
| 0.379         | 13.0  | 11375 | 0.1536          | 0.1905 |
| 0.3793        | 14.0  | 12250 | 0.1517          | 0.1888 |
| 0.3709        | 15.0  | 13125 | 0.1512          | 0.1882 |
| 0.3702        | 16.0  | 14000 | 0.1499          | 0.1858 |
| 0.367         | 17.0  | 14875 | 0.1492          | 0.1848 |
| 0.3656        | 18.0  | 15750 | 0.1493          | 0.1842 |
| 0.3604        | 19.0  | 16625 | 0.1485          | 0.1825 |
| 0.3671        | 20.0  | 17500 | 0.1481          | 0.1833 |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.4.0+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1