---
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: 0.1603
- Wer: 0.1145

## 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    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 1.0491        | 0.47  | 600   | 0.3405          | 0.4429 |
| 0.1667        | 0.95  | 1200  | 0.2590          | 0.3481 |
| 0.1213        | 1.42  | 1800  | 0.2217          | 0.3055 |
| 0.1021        | 1.9   | 2400  | 0.1943          | 0.2839 |
| 0.0822        | 2.37  | 3000  | 0.1861          | 0.2341 |
| 0.0739        | 2.85  | 3600  | 0.1681          | 0.2302 |
| 0.062         | 3.32  | 4200  | 0.1669          | 0.2065 |
| 0.0543        | 3.8   | 4800  | 0.1727          | 0.2115 |
| 0.0434        | 4.27  | 5400  | 0.1581          | 0.1826 |
| 0.0378        | 4.74  | 6000  | 0.1544          | 0.1963 |
| 0.0349        | 5.22  | 6600  | 0.1415          | 0.1680 |
| 0.0266        | 5.69  | 7200  | 0.1504          | 0.1607 |
| 0.0226        | 6.17  | 7800  | 0.1471          | 0.1485 |
| 0.0186        | 6.64  | 8400  | 0.1435          | 0.1456 |
| 0.0163        | 7.12  | 9000  | 0.1415          | 0.1331 |
| 0.0117        | 7.59  | 9600  | 0.1413          | 0.1309 |
| 0.0119        | 8.07  | 10200 | 0.1618          | 0.1214 |
| 0.0076        | 8.54  | 10800 | 0.1545          | 0.1194 |
| 0.0068        | 9.02  | 11400 | 0.1553          | 0.1204 |
| 0.0038        | 9.49  | 12000 | 0.1584          | 0.1177 |
| 0.0036        | 9.96  | 12600 | 0.1603          | 0.1145 |


### Framework versions

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