---
license: mit
base_model: facebook/w2v-bert-2.0
tags:
- generated_from_trainer
metrics:
- wer
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: 0.1651
- Wer: 0.1279

## 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    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 1.4399        | 0.46  | 600   | 0.3709          | 0.4586 |
| 0.1715        | 0.92  | 1200  | 0.2427          | 0.3379 |
| 0.1226        | 1.38  | 1800  | 0.2216          | 0.2919 |
| 0.1073        | 1.84  | 2400  | 0.1992          | 0.2672 |
| 0.0888        | 2.3   | 3000  | 0.1835          | 0.2506 |
| 0.0781        | 2.76  | 3600  | 0.1768          | 0.2491 |
| 0.0671        | 3.22  | 4200  | 0.1702          | 0.2309 |
| 0.0575        | 3.68  | 4800  | 0.1784          | 0.2202 |
| 0.0531        | 4.14  | 5400  | 0.1690          | 0.1881 |
| 0.0421        | 4.6   | 6000  | 0.1707          | 0.1876 |
| 0.0398        | 5.06  | 6600  | 0.1672          | 0.1759 |
| 0.0305        | 5.52  | 7200  | 0.1516          | 0.1575 |
| 0.0306        | 5.98  | 7800  | 0.1576          | 0.1682 |
| 0.0219        | 6.44  | 8400  | 0.1516          | 0.1610 |
| 0.021         | 6.9   | 9000  | 0.1418          | 0.1493 |
| 0.0151        | 7.36  | 9600  | 0.1343          | 0.1359 |
| 0.0133        | 7.82  | 10200 | 0.1410          | 0.1433 |
| 0.0103        | 8.28  | 10800 | 0.1564          | 0.1386 |
| 0.0084        | 8.74  | 11400 | 0.1546          | 0.1276 |
| 0.0067        | 9.2   | 12000 | 0.1622          | 0.1244 |
| 0.0043        | 9.66  | 12600 | 0.1651          | 0.1279 |


### Framework versions

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