---
base_model: facebook/mms-1b-all
datasets:
- common_voice_17_0
library_name: transformers
license: cc-by-nc-4.0
metrics:
- wer
- bleu
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-mms-1b-CV17.0-training_set_variations
  results:
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: common_voice_17_0
      type: common_voice_17_0
      config: ta
      split: validation
      args: ta
    metrics:
    - type: wer
      value: 0.4582664894348444
      name: Wer
    - type: bleu
      value: 0.3001349308741465
      name: Bleu
---

<!-- 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-mms-1b-CV17.0-training_set_variations

This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_17_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4355
- Wer: 0.4583
- Cer: 0.0787
- Bleu: 0.3001

## 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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.15
- training_steps: 2000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    | Bleu   |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|
| 12.8763       | 25.0  | 50   | 4.9690          | 1.0000 | 0.9319 | 0.0    |
| 2.2038        | 50.0  | 100  | 0.3040          | 0.4239 | 0.0696 | 0.3337 |
| 0.1153        | 75.0  | 150  | 0.2911          | 0.4134 | 0.0685 | 0.3474 |
| 0.0557        | 100.0 | 200  | 0.3344          | 0.4333 | 0.0718 | 0.3271 |
| 0.0448        | 125.0 | 250  | 0.3486          | 0.4403 | 0.0743 | 0.3213 |
| 0.0382        | 150.0 | 300  | 0.3938          | 0.4499 | 0.0762 | 0.3102 |
| 0.0364        | 175.0 | 350  | 0.3927          | 0.4525 | 0.0778 | 0.3045 |
| 0.0286        | 200.0 | 400  | 0.3883          | 0.4417 | 0.0744 | 0.3173 |
| 0.0293        | 225.0 | 450  | 0.4235          | 0.4656 | 0.0794 | 0.2913 |
| 0.0296        | 250.0 | 500  | 0.4432          | 0.4710 | 0.0817 | 0.2771 |
| 0.0302        | 275.0 | 550  | 0.4266          | 0.4524 | 0.0765 | 0.3016 |
| 0.0252        | 300.0 | 600  | 0.4376          | 0.4717 | 0.0815 | 0.2793 |
| 0.0216        | 325.0 | 650  | 0.4355          | 0.4583 | 0.0787 | 0.3001 |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1