---
library_name: transformers
language:
- am
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
- surafelabebe/fleurs_am
metrics:
- wer
model-index:
- name: Whisper Small Am - Surafel Worku
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Common Voice 17.0
      type: mozilla-foundation/common_voice_17_0
      args: 'config: am, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 50.96566523605151
---

<!-- 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. -->

# Whisper Small Amharic

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the [Common Voice 17.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/viewer/am?views%5B%5D=am_train) and [surafelabebe/fleurs_am](https://huggingface.co/datasets/surafelabebe/fleurs_am) (a subset of [google/fleurs](https://huggingface.co/datasets/google/fleurs)) datasets.
It achieves the following results on the evaluation set:
- Loss: 0.4352
- Wer: 50.9657

## Model description

The model was trained for 10 hours on T4 GPU. Training results indicate potential overfitting. Future improvements will focus on mitigating this by incorporating a larger dataset, extended training epochs, and dropout regularization.


### Usage

```python
from transformers import pipeline

pipe = pipeline(model="surafelabebe/whisper-small-am")

text = pipe("sample.wav")["text"]  # change to "your audio file name"

print(text)
```

| Input                                                                                                                                          | Output Transcript                                                                              |
|:----------------------------------------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------:|
| <audio controls><source src="https://huggingface.co/spaces/surafelabebe/audio_samples/resolve/main/audio_0.wav" type="audio/wav"></audio>       | አቶ ቦጋለ መብራቱ ወይዘሮ ውድነሽ በታሙም ባገቡ በሁለተኛው አመት መጫረሻ ወንድሪክ ሰውለደላቸውን   | 
| <audio controls><source src="https://huggingface.co/spaces/surafelabebe/audio_samples/resolve/main/audio_1.wav" type="audio/wav"></audio>       | ከሰብ ለሚሁን ከወይዘሮ ትሩ ወይም ከአብት ሺሰር ጋር ልዩሩ ጉዳይ ኖሮት አይደለም                    |

## Training procedure

The fine-tuning process followed a similar procedure to that described in [this](https://huggingface.co/blog/fine-tune-whisper) blog post.

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.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_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer     |
|:-------------:|:-------:|:----:|:---------------:|:-------:|
| 0.0108        | 9.6154  | 1000 | 0.3446          | 54.9759 |
| 0.0009        | 19.2308 | 2000 | 0.4052          | 51.7570 |
| 0.0001        | 28.8462 | 3000 | 0.4277          | 50.9388 |
| 0.0001        | 38.4615 | 4000 | 0.4352          | 50.9657 |


### Framework versions

- Transformers 4.49.0
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0