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

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: 0.1738
- Wer: 0.1162

## 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    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 1.1027        | 0.47  | 600   | 0.3414          | 0.4257 |
| 0.1646        | 0.95  | 1200  | 0.2676          | 0.3585 |
| 0.1197        | 1.42  | 1800  | 0.2197          | 0.2988 |
| 0.1028        | 1.9   | 2400  | 0.2114          | 0.2849 |
| 0.0809        | 2.37  | 3000  | 0.1947          | 0.2478 |
| 0.0738        | 2.85  | 3600  | 0.1593          | 0.2411 |
| 0.0615        | 3.32  | 4200  | 0.1657          | 0.2075 |
| 0.0528        | 3.8   | 4800  | 0.1587          | 0.1986 |
| 0.0425        | 4.27  | 5400  | 0.1687          | 0.1749 |
| 0.0377        | 4.74  | 6000  | 0.1566          | 0.1796 |
| 0.0336        | 5.22  | 6600  | 0.1628          | 0.1647 |
| 0.0269        | 5.69  | 7200  | 0.1580          | 0.1754 |
| 0.0237        | 6.17  | 7800  | 0.1564          | 0.1530 |
| 0.0189        | 6.64  | 8400  | 0.1593          | 0.1446 |
| 0.0159        | 7.12  | 9000  | 0.1370          | 0.1376 |
| 0.0118        | 7.59  | 9600  | 0.1586          | 0.1421 |
| 0.012         | 8.07  | 10200 | 0.1567          | 0.1281 |
| 0.0071        | 8.54  | 10800 | 0.1645          | 0.1227 |
| 0.0072        | 9.02  | 11400 | 0.1634          | 0.1202 |
| 0.0036        | 9.49  | 12000 | 0.1719          | 0.1189 |
| 0.0036        | 9.96  | 12600 | 0.1738          | 0.1162 |


### Framework versions

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