AIbase
EN
Home
Malaya Speech Fine Tune Realcase 30 Jun Lm
M

Malaya Speech Fine Tune Realcase 30 Jun Lm

Developed by RuiqianLi
This model is a fine-tuned version of malay-huggingface/wav2vec2-xls-r-300m-mixed on the uob_singlish dataset, mainly used for speech recognition tasks.
Speech Recognition
Transformers
#Singapore English recognition#Low-resource speech transcription#Multidialect adaptation
Downloads 71
Release Time : 6/30/2022

Model Overview

This is a speech recognition model fine-tuned based on the wav2vec2-xls-r-300m-mixed model, trained on the uob_singlish dataset, and supports Singapore English recognition.

Model Features

Singapore English support
Optimized specifically for the accent and dialect characteristics of Singapore English
Efficient fine-tuning
Efficient fine-tuning based on the pre-trained model to reduce training costs
Medium scale
300M parameter scale, achieving a balance between accuracy and computational efficiency

Model Capabilities

Singapore English speech recognition
Automatic speech-to-text conversion
Accent adaptability processing

Use Cases

Speech transcription
Transcription of Singapore English conversations
Convert conversations containing Singapore English accents into text
Word Error Rate (WER) 0.3194
Voice assistant
Localized voice assistant
Develop a voice assistant that can understand local accents for the Singapore region
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase