---
license: cc-by-nc-4.0
base_model: facebook/mms-1b-all
tags:
- generated_from_trainer
datasets:
- common_voice_11_0
metrics:
- wer
model-index:
- name: model_mms
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: common_voice_11_0
      type: common_voice_11_0
      config: tr
      split: test[:10]
      args: tr
    metrics:
    - name: Wer
      type: wer
      value: 0.44285714285714284
---

<!-- 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. -->

# model_mms

This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co./facebook/mms-1b-all) on the common_voice_11_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4310
- Wer: 0.4429

## 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: 0.001
- train_batch_size: 32
- 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: 1
- num_epochs: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2499        | 0.12  | 100  | 0.4539          | 0.4714 |
| 0.2405        | 0.25  | 200  | 0.4487          | 0.4429 |
| 0.235         | 0.37  | 300  | 0.4289          | 0.4143 |
| 0.2432        | 0.49  | 400  | 0.4239          | 0.4    |
| 0.2373        | 0.61  | 500  | 0.4380          | 0.4429 |
| 0.2341        | 0.74  | 600  | 0.4435          | 0.4286 |
| 0.2333        | 0.86  | 700  | 0.4459          | 0.4429 |
| 0.2348        | 0.98  | 800  | 0.4310          | 0.4429 |


### Framework versions

- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0