---
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: 0.1771
- Wer: 0.1179

## 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    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 1.1594        | 0.46  | 600   | 0.3721          | 0.4705 |
| 0.1751        | 0.92  | 1200  | 0.2652          | 0.3615 |
| 0.1269        | 1.38  | 1800  | 0.2069          | 0.2824 |
| 0.1113        | 1.84  | 2400  | 0.1867          | 0.2535 |
| 0.0904        | 2.3   | 3000  | 0.1907          | 0.2555 |
| 0.0783        | 2.76  | 3600  | 0.1740          | 0.2421 |
| 0.0691        | 3.22  | 4200  | 0.1860          | 0.2366 |
| 0.0588        | 3.68  | 4800  | 0.1696          | 0.2195 |
| 0.0541        | 4.14  | 5400  | 0.1560          | 0.1859 |
| 0.0421        | 4.6   | 6000  | 0.1812          | 0.1757 |
| 0.0385        | 5.06  | 6600  | 0.1643          | 0.1677 |
| 0.0305        | 5.52  | 7200  | 0.1457          | 0.1553 |
| 0.0309        | 5.98  | 7800  | 0.1494          | 0.1558 |
| 0.0214        | 6.44  | 8400  | 0.1516          | 0.1428 |
| 0.0216        | 6.9   | 9000  | 0.1409          | 0.1408 |
| 0.0146        | 7.36  | 9600  | 0.1524          | 0.1359 |
| 0.0133        | 7.82  | 10200 | 0.1494          | 0.1294 |
| 0.0103        | 8.28  | 10800 | 0.1600          | 0.1321 |
| 0.0079        | 8.74  | 11400 | 0.1658          | 0.1224 |
| 0.0065        | 9.2   | 12000 | 0.1644          | 0.1227 |
| 0.0043        | 9.66  | 12600 | 0.1771          | 0.1179 |


### Framework versions

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