---
language:
- fa
library_name: hezar
tags:
- automatic-speech-recognition
- hezar
datasets:
- mozilla-foundation/common_voice_11_0
pipeline_tag: automatic-speech-recognition
---
Whisper (small) model finetuned on Common Voice by Hezar AI.

## Usage
```
pip install hezar
```
```python
from hezar.models import Model

whisper = Model.load("hezarai/whisper-small-fa")
transcripts = whisper.predict("speech_example.mp3")
print(transcripts)
```