Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Efficient fine Tuning of Whisper for Algerian Dialect Automatic Speech Recognition using Low Rank Adaptation

Domain:

natural language processing

Record type:

model
Creator:
M.BA.NF. A.M
Publisher:
IEEE
Host:

Visit

doi.org

Tasks

automatic speech recognitionspeech processing

Languages

Arabic, Algerian Spoken

Licenses

https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.htmlhttps://doi.org/10.15223/policy-029https://doi.org/10.15223/policy-037

Similar

sykeb21/Fine-Tuning-OpenAI-Whisper-for-Amharic-Speech-RecognitionParameter-Efficient Fine-Tuning of the Google Gemma-7B Model for Hausa Language Sentiment Analysis Task Using Low-Rank Adaptation TechniqueFine-tuning Whisper Tiny for Swahili ASR: Challenges and Recommendations for Low-Resource Speech RecognitionRobust Assamese Speech Recognition through Controlled Fine-Tuning of Whisper ModelsFull Fine-Tuning vs. Parameter-Efficient Adaptation for Low-Resource African ASR: A Controlled Study with Whisper-SmallAfrikaans Speech Dataset for Whisper Fine-Tuning

sykeb21/Fine-Tuning-OpenAI-Whisper-for-Amharic-Speech-Recognition

This repository contains a complete, memory-optimized pipeline for fine-tuning OpenAI’s Whisper auto

Parameter-Efficient Fine-Tuning of the Google Gemma-7B Model for Hausa Language Sentiment Analysis Task Using Low-Rank Adaptation Technique

Fine-tuning Whisper Tiny for Swahili ASR: Challenges and Recommendations for Low-Resource Speech Recognition

Robust Assamese Speech Recognition through Controlled Fine-Tuning of Whisper Models

Developing Automatic Speech Recognition (ASR) for morphologically rich, low-resource languages such

Full Fine-Tuning vs. Parameter-Efficient Adaptation for Low-Resource African ASR: A Controlled Study with Whisper-Small

Afrikaans Speech Dataset for Whisper Fine-Tuning

Dataset Card This dataset consists of approximately 56 hours of Afrikaans speech extracted from chu