AIbase
EN
Home
Wav2vec2 Large Xls R 300m Singlish Colab
W

Wav2vec2 Large Xls R 300m Singlish Colab

Developed by RuiqianLi
A speech recognition model fine-tuned on the Singapore English (li_singlish) dataset based on facebook/wav2vec2-xls-r-300m
Speech Recognition
Transformers
Open Source License:Apache-2.0#Singapore English Speech Recognition#Low-resource Speech Model#Multi-dialect Adaptation
Downloads 22
Release Time : 5/18/2022

Model Overview

This model is an automatic speech recognition (ASR) model optimized for Singapore English, fine-tuned on the li_singlish dataset, suitable for speech-to-text tasks with Singapore English accents

Model Features

Singapore English Optimization
Specially fine-tuned for Singapore English accents and dialect characteristics
Efficient Training
Optimized training process using gradient accumulation and mixed-precision training techniques
Performance Balance
Achieves a good balance between model size and recognition accuracy

Model Capabilities

Singapore English Speech Recognition
Speech-to-Text
Accent Adaptation

Use Cases

Speech Transcription
Singapore English Speech Transcription
Convert Singapore English accented speech into text
Word Error Rate (WER) 0.3337
Voice Assistants
Singapore Regional Voice Assistant
Develop more accurate voice assistants for the Singapore region
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase