STT-Whisper-Pashto

Fine-tuned Whisper model for Pashto Speech Recognition.

Base Model

• Whisper Small

Training Method

• LoRA Fine-Tuning

Dataset

Pashto ASR Dataset

• Kaggle: https://www.kaggle.com/datasets/itssabtain/pashto-asr-dataset (Recommended)
• Hugging Face: https://huggingface.co/datasets/Sabtain-Dev/Pashto-ASR-Dataset

Best Result

WER: 43.83%

Usage

from transformers import WhisperProcessor
from transformers import WhisperForConditionalGeneration

processor = WhisperProcessor.from_pretrained(
    "Sabtain-Dev/STT-Whisper-Pashto"
)

model = WhisperForConditionalGeneration.from_pretrained(
    "Sabtain-Dev/STT-Whisper-Pashto"
)