Afrikaans Speech Dataset for Whisper Fine-Tuning

Domaine:

natural language processing

Type de record:

dataset

Créateur:

and

Hôte:

Dataset Card This dataset consists of approximately 56 hours of Afrikaans speech extracted from church sermons, paired with cleaned and aligned transcripts. It is specifically prepared for fine-tuning multilingual ASR models like OpenAI's Whisper (particularly large-v3) on low-resource Afrikaans speech

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

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

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

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

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

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

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

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

Afrikaans Speech Dataset for Whisper Fine-Tuning

Domaine:

Type de record:

Visit

Tasks

Languages

Tags

Licenses

Similaires

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

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

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

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

Abdelelta/Luganda-whisper-fine-tuning

Fine-Tuning Whisper for Speech Translation: A Case Study on Translating Darija to Arabic