AIbase
EN
Home
Whisper Small Chinese Base
W

Whisper Small Chinese Base

Developed by Jingmiao
A Chinese speech recognition model fine-tuned on the google/fleurs cmn_hans_cn dataset based on openai/whisper-small
Speech Recognition
Transformers
Open Source License:Apache-2.0#Chinese speech recognition#Low character error rate#Fleurs fine-tuning
Downloads 117
Release Time : 12/17/2022

Model Overview

This model is a small version of Whisper optimized for Chinese speech recognition tasks and performs well in Mandarin recognition tasks

Model Features

Chinese optimization
Specifically fine-tuned and optimized for Chinese Mandarin speech recognition
Efficient performance
Achieve a character error rate of 16.64% while keeping the model small
Mixed precision training
Adopt the native automatic mixed precision training technology to improve training efficiency

Model Capabilities

Chinese speech-to-text
Mandarin recognition
Continuous speech recognition

Use Cases

Speech transcription
Meeting minutes
Automatically convert Chinese meeting recordings into text records
The character error rate is about 16.64%
Voice notes
Convert user voice input into editable text
Voice assistant
Chinese voice command recognition
Provide Chinese voice command recognition capabilities for smart devices
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