---
library_name: transformers
base_model: KasuleTrevor/wav2vec2-xls-r-300m-nyn_filtered-yogera-v3
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: Luganda_speech_to_intent_nyn_xlsr
  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. -->

# Luganda_speech_to_intent_nyn_xlsr

This model is a fine-tuned version of [KasuleTrevor/wav2vec2-xls-r-300m-nyn_filtered-yogera-v3](https://huggingface.co/KasuleTrevor/wav2vec2-xls-r-300m-nyn_filtered-yogera-v3) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1401
- Accuracy: 0.9757
- Precision: 0.9761
- Recall: 0.9757
- F1: 0.9755

## 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: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 2.9405        | 1.0   | 131  | 2.3617          | 0.5163   | 0.4655    | 0.5163 | 0.4450 |
| 1.9336        | 2.0   | 262  | 0.1540          | 0.9859   | 0.9865    | 0.9859 | 0.9858 |
| 0.3581        | 3.0   | 393  | 0.0748          | 0.9902   | 0.9904    | 0.9902 | 0.9902 |
| 0.1253        | 4.0   | 524  | 0.0730          | 0.9881   | 0.9884    | 0.9881 | 0.9881 |
| 0.1166        | 5.0   | 655  | 0.0609          | 0.9913   | 0.9915    | 0.9913 | 0.9913 |
| 0.1071        | 6.0   | 786  | 0.0667          | 0.9913   | 0.9915    | 0.9913 | 0.9913 |
| 0.0836        | 7.0   | 917  | 0.0601          | 0.9902   | 0.9904    | 0.9902 | 0.9902 |
| 0.0736        | 8.0   | 1048 | 0.0611          | 0.9913   | 0.9915    | 0.9913 | 0.9913 |
| 0.0612        | 9.0   | 1179 | 0.0633          | 0.9902   | 0.9904    | 0.9902 | 0.9902 |
| 0.0553        | 10.0  | 1310 | 0.0657          | 0.9902   | 0.9904    | 0.9902 | 0.9902 |
| 0.0478        | 11.0  | 1441 | 0.0650          | 0.9913   | 0.9915    | 0.9913 | 0.9913 |
| 0.0392        | 12.0  | 1572 | 0.0681          | 0.9902   | 0.9904    | 0.9902 | 0.9902 |


### Framework versions

- Transformers 4.51.3
- Pytorch 2.1.0+cu118
- Datasets 3.6.0
- Tokenizers 0.21.2