# Multi-round fine-tuning

An Arabic (Tunisian dialect) speech recognition model fine-tuned on the AT_ENT dataset based on openai/whisper-medium

A speech recognition model fine-tuned on Darija dialect speech-to-text dataset based on openai/whisper-medium

An English-Spanish translation model fine-tuned based on facebook/mbart-large-50, achieving a BLEU score of 45.03 on the evaluation set.

A text summarization model fine-tuned based on google/long-t5-tglobal-base, performing well on XSum and CNN/DailyMail datasets.

This is a Turkish speech recognition model based on the wav2vec2 architecture, fine-tuned on the Common Voice dataset with a word error rate (WER) of 0.3634.

This model is an automatic speech recognition (ASR) model fine-tuned on the Mozilla Common Voice 7.0 Persian dataset, specifically designed for Persian speech-to-text tasks.

A Bengali speech recognition model fine-tuned from facebook/wav2vec2-xls-r-300m, specializing in command word recognition

Automatic speech recognition model fine-tuned based on the Persian Common Voice dataset

Arabic grammar error correction model fine-tuned based on aubmindlab/bert-base-arabertv02

MNLI task model fine-tuned on DeBERTa-v3-large, achieving 91.75% accuracy on the GLUE MNLI evaluation set