---
license: cc-by-nc-4.0
base_model: facebook/mms-1b
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- wer
model-index:
- name: results
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: audiofolder
      type: audiofolder
      config: default
      split: test
      args: default
    metrics:
    - name: Wer
      type: wer
      value: 0.5569807597434633
---

<!-- 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. -->

# results

This model is a fine-tuned version of [facebook/mms-1b](https://huggingface.co/facebook/mms-1b) on the audiofolder dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5862
- Wer: 0.5570
- Cer: 0.2802

## 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: 0.0003
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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    | Cer    |
|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
| 3.6617        | 1.6495  | 40   | 3.4133          | 0.9941 | 0.8573 |
| 3.0704        | 3.2990  | 80   | 3.0021          | 1.0    | 0.9985 |
| 2.8663        | 4.9485  | 120  | 2.8530          | 0.9531 | 0.7800 |
| 1.995         | 6.5979  | 160  | 1.8117          | 0.9260 | 0.5088 |
| 1.3171        | 8.2474  | 200  | 1.3296          | 0.6744 | 0.2939 |
| 1.0979        | 9.8969  | 240  | 1.2741          | 0.5787 | 0.2667 |
| 0.9623        | 11.5464 | 280  | 1.2679          | 0.5570 | 0.2624 |
| 0.8367        | 13.1959 | 320  | 1.3316          | 0.5910 | 0.2622 |
| 0.7728        | 14.8454 | 360  | 1.4157          | 0.5575 | 0.2705 |
| 0.5491        | 16.4948 | 400  | 1.5152          | 0.5668 | 0.2760 |
| 0.5494        | 18.1443 | 440  | 1.6297          | 0.5417 | 0.2683 |
| 0.5065        | 19.7938 | 480  | 1.5862          | 0.5570 | 0.2802 |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1