---
license: apache-2.0
tags:
- generated_from_trainer
base_model: facebook/wav2vec2-base
metrics:
- wer
model-index:
- name: krishivoice
  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. -->

# krishivoice

This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6028
- Wer: 0.3862

## 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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 100
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step  | Validation Loss | Wer    |
|:-------------:|:-------:|:-----:|:---------------:|:------:|
| 3.0141        | 4.5455  | 500   | 4.3443          | 1.0    |
| 2.9159        | 9.0909  | 1000  | 3.3390          | 1.0    |
| 2.2697        | 13.6364 | 1500  | 2.3303          | 0.9577 |
| 1.2118        | 18.1818 | 2000  | 1.4385          | 0.7634 |
| 0.8524        | 22.7273 | 2500  | 1.0982          | 0.6593 |
| 0.6842        | 27.2727 | 3000  | 0.9136          | 0.6028 |
| 0.5746        | 31.8182 | 3500  | 0.8810          | 0.5732 |
| 0.4857        | 36.3636 | 4000  | 0.8336          | 0.5443 |
| 0.417         | 40.9091 | 4500  | 0.7018          | 0.5016 |
| 0.3794        | 45.4545 | 5000  | 0.5961          | 0.4667 |
| 0.3366        | 50.0    | 5500  | 0.6209          | 0.4585 |
| 0.3044        | 54.5455 | 6000  | 0.5942          | 0.4407 |
| 0.2783        | 59.0909 | 6500  | 0.5895          | 0.4313 |
| 0.2626        | 63.6364 | 7000  | 0.6304          | 0.4350 |
| 0.2402        | 68.1818 | 7500  | 0.6373          | 0.4215 |
| 0.2287        | 72.7273 | 8000  | 0.5945          | 0.4033 |
| 0.2173        | 77.2727 | 8500  | 0.6297          | 0.4126 |
| 0.2059        | 81.8182 | 9000  | 0.6149          | 0.3951 |
| 0.1924        | 86.3636 | 9500  | 0.6083          | 0.3967 |
| 0.2043        | 90.9091 | 10000 | 0.5965          | 0.3866 |
| 0.1913        | 95.4545 | 10500 | 0.6082          | 0.3890 |
| 0.1934        | 100.0   | 11000 | 0.6028          | 0.3862 |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1