AIbase
EN
Home
Whisper Large V2 Mn 13
W

Whisper Large V2 Mn 13

Developed by bayartsogt
A Mongolian speech recognition model fine-tuned on Mongolian datasets based on OpenAI's whisper-large-v2 model, supporting automatic speech recognition tasks in Mongolian.
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Mongolian speech recognition#Low character error rate#Multi-dataset training
Downloads 161
Release Time : 12/20/2022

Model Overview

This is an automatic speech recognition (ASR) model specifically optimized for Mongolian, fine-tuned on multiple Mongolian datasets, capable of converting Mongolian speech into text.

Model Features

Mongolian optimization
Specially optimized and fine-tuned for the characteristics of Mongolian speech
Multi-dataset training
Trained on multiple Mongolian datasets including Common Voice and FLEURS
Low error rate
Achieves low word error rate (WER) and character error rate (CER) on test sets

Model Capabilities

Mongolian speech recognition
Speech-to-text

Use Cases

Speech transcription
Mongolian speech transcription
Convert Mongolian speech content into text
Word error rate 20.02%, character error rate 6.60%
Voice assistant
Mongolian voice interaction
Used to develop voice assistant applications supporting Mongolian
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