Efficient fine-tuning of whisper models for Amazigh ASR: leveraging LoRA and its variants

Type de record:

paper

Créateur:

MohFadEl

Éditeur:

Spr

Hôte:

Visit

Tasks

automatic speech recognition speech processing

Languages

Licenses

https://www.springernature.com/gp/researchers/text-and-data-mining https://www.springernature.com/gp/researchers/text-and-data-mining

Similaires

An Integrated Semi-Supervised Framework for Low-Resource Language ASR: Acoustic Enhancement, LoRA Fine-Tuning, and Hybrid Post-Processing for Amazigh VariantsJONAHKYAGABA/-Whisper-ASR-Fine-Tuning-for-AmharicFull Fine-Tuning vs. Parameter-Efficient Adaptation for Low-Resource African ASR: A Controlled Study with Whisper-SmallAV55CS/Speech-to-Text-Fine-tuning-Whisper-Tiny-for-Swahili-ASROptimizing Whisper models for Amazigh ASR: a comparative analysisFine-tuning Whisper Tiny for Swahili ASR: Challenges and Recommendations for Low-Resource Speech Recognition

An Integrated Semi-Supervised Framework for Low-Resource Language ASR: Acoustic Enhancement, LoRA Fine-Tuning, and Hybrid Post-Processing for Amazigh Variants

JONAHKYAGABA/-Whisper-ASR-Fine-Tuning-for-Amharic

# 🗣️ Whisper ASR Fine-Tuning for Amharic # 🗣️ Whisper ASR Fine-Tuning for Amharic This project imp

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

AV55CS/Speech-to-Text-Fine-tuning-Whisper-Tiny-for-Swahili-ASR

ASR-Low resource Language-Swahili # Swahili Speech Recognition - Whisper Fine-tuning This reposito

Optimizing Whisper models for Amazigh ASR: a comparative analysis

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