---
library_name: transformers
license: mit
base_model: facebook/w2v-bert-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: w2v-bert-2.0-test
  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. -->

# w2v-bert-2.0-test

This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2815
- Wer: 0.2494
- Cer: 0.0627

## 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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
| 0.8172        | 1.0   | 1473 | 0.3534          | 0.3020 | 0.0763 |
| 0.2395        | 2.0   | 2946 | 0.2995          | 0.2780 | 0.0701 |
| 0.1948        | 3.0   | 4419 | 0.2876          | 0.2576 | 0.0649 |
| 0.1665        | 4.0   | 5892 | 0.2886          | 0.2583 | 0.0640 |
| 0.1462        | 5.0   | 7365 | 0.2815          | 0.2494 | 0.0627 |


### Framework versions

- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1