---
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- audio-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-base-lang-id
  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. -->

# wav2vec2-base-lang-id

This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the /content/dataset dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0134
- Accuracy: 0.998

## 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: 4e-05
- train_batch_size: 24
- eval_batch_size: 4
- seed: 0
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 48
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 200
- num_epochs: 5.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 0.0677        | 1.0    | 601  | 0.0297          | 0.9935   |
| 0.0345        | 2.0    | 1202 | 0.0362          | 0.9935   |
| 0.013         | 3.0    | 1803 | 0.0151          | 0.997    |
| 0.0003        | 4.0    | 2404 | 0.0134          | 0.998    |
| 0.0003        | 4.9925 | 3000 | 0.0127          | 0.998    |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0