---
license: apache-2.0
base_model: Samuael/asr-alffamharic-phoneme-based
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: asr-alffamharic-phoneme-based
  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. -->

# asr-alffamharic-phoneme-based

This model is a fine-tuned version of [Samuael/asr-alffamharic-phoneme-based](https://huggingface.co/Samuael/asr-alffamharic-phoneme-based) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3396
- Wer: 0.4617

## 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: 0.0005
- train_batch_size: 32
- 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: 1000
- num_epochs: 20

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.3593        | 1.31  | 200  | 0.3335          | 0.4799 |
| 0.3037        | 2.61  | 400  | 0.3348          | 0.4808 |
| 0.3754        | 3.92  | 600  | 0.3330          | 0.4813 |
| 0.4145        | 5.23  | 800  | 0.3314          | 0.4760 |
| 0.3096        | 6.54  | 1000 | 0.3366          | 0.4717 |
| 0.3487        | 7.84  | 1200 | 0.3360          | 0.4691 |
| 0.2905        | 9.15  | 1400 | 0.3349          | 0.4687 |
| 0.3085        | 10.46 | 1600 | 0.3400          | 0.4701 |
| 0.2703        | 11.76 | 1800 | 0.3351          | 0.4727 |
| 0.282         | 13.07 | 2000 | 0.3380          | 0.4663 |
| 0.2757        | 14.38 | 2200 | 0.3398          | 0.4662 |
| 0.2573        | 15.69 | 2400 | 0.3404          | 0.4614 |
| 0.3661        | 16.99 | 2600 | 0.3390          | 0.4612 |
| 0.2983        | 18.3  | 2800 | 0.3389          | 0.4596 |
| 0.2578        | 19.61 | 3000 | 0.3396          | 0.4617 |


### Framework versions

- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1