---
license: mit
tags:
- generated_from_trainer
metrics:
- wer
base_model: facebook/w2v-bert-2.0
model-index:
- name: w2v-bert-2.0-nonstudio_and_studioRecords
  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-nonstudio_and_studioRecords

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: 0.1679
- Wer: 0.1214

## 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: 5e-05
- 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_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Wer    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 1.1162        | 0.46  | 600   | 0.4548          | 0.5036 |
| 0.1745        | 0.92  | 1200  | 0.2634          | 0.3735 |
| 0.1268        | 1.38  | 1800  | 0.2148          | 0.2951 |
| 0.1106        | 1.84  | 2400  | 0.2106          | 0.2677 |
| 0.0917        | 2.3   | 3000  | 0.1963          | 0.2466 |
| 0.0794        | 2.76  | 3600  | 0.1789          | 0.2441 |
| 0.0688        | 3.22  | 4200  | 0.1911          | 0.2371 |
| 0.0586        | 3.68  | 4800  | 0.1774          | 0.2013 |
| 0.0534        | 4.14  | 5400  | 0.1567          | 0.1876 |
| 0.0417        | 4.6   | 6000  | 0.1733          | 0.1804 |
| 0.0396        | 5.06  | 6600  | 0.1537          | 0.1595 |
| 0.0302        | 5.52  | 7200  | 0.1559          | 0.1545 |
| 0.03          | 5.98  | 7800  | 0.1482          | 0.1560 |
| 0.0214        | 6.44  | 8400  | 0.1554          | 0.1622 |
| 0.0209        | 6.9   | 9000  | 0.1464          | 0.1433 |
| 0.015         | 7.36  | 9600  | 0.1626          | 0.1386 |
| 0.0129        | 7.82  | 10200 | 0.1601          | 0.1331 |
| 0.0105        | 8.28  | 10800 | 0.1651          | 0.1373 |
| 0.0078        | 8.74  | 11400 | 0.1600          | 0.1237 |
| 0.0061        | 9.2   | 12000 | 0.1694          | 0.1269 |
| 0.004         | 9.66  | 12600 | 0.1679          | 0.1214 |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.1.1+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1