# Whisper architecture optimization

A Tajik automatic speech recognition model fine-tuned from OpenAI Whisper-small, trained on Google Fleurs dataset with a word error rate of 24.26%.

Uzbek speech recognition model fine-tuned on Whisper Base, trained on the Common Voice dataset

This model is an automatic speech recognition (ASR) model fine-tuned on the Azerbaijani Common Voice 17.0 dataset based on OpenAI's Whisper Large v3, achieving a word error rate (WER) of 1.195%.

Hamsa is an Arabic speech recognition model built on the Whisper architecture, focusing on the linguistic needs of the Middle East and North Africa region.

Hindi speech recognition model fine-tuned based on OpenAI Whisper-large-v2, trained on multiple public Hindi ASR corpora

A Mongolian speech recognition model fine-tuned on Mongolian datasets based on OpenAI's whisper-large-v2 model, supporting automatic speech recognition tasks in Mongolian.