AIbase
EN
Home
Whisper Large V2 Cantonese
W

Whisper Large V2 Cantonese

Developed by simonl0909
An automatic speech recognition model fine-tuned on Cantonese dataset based on OpenAI Whisper Large V2, achieving a character error rate of 6.7274% on the test set
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Cantonese speech recognition#Low character error rate#Common Voice fine-tuning
Downloads 131
Release Time : 12/11/2022

Model Overview

Speech recognition model specifically optimized for Cantonese, suitable for Cantonese speech-to-text tasks

Model Features

Cantonese optimization
Fine-tuned on Common Voice Cantonese dataset, specifically optimized for Cantonese speech recognition
Low error rate
Achieves a character error rate (CER) of 6.7274% on the test set, demonstrating excellent performance
Based on Whisper architecture
Built upon the powerful Whisper Large V2 base model, inheriting its outstanding speech recognition capabilities

Model Capabilities

Cantonese speech recognition
Speech-to-text
Automatic speech transcription

Use Cases

Speech transcription
Cantonese meeting minutes
Automatically transcribe Cantonese meeting content into written records
Character error rate 6.7274%
Cantonese media subtitle generation
Automatically generate subtitles for Cantonese video content
Voice assistant
Cantonese voice interaction
Supports Cantonese voice command recognition
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