AIbase
EN
Home
Training V2
T

Training V2

Developed by SofiaK
A speech recognition model fine-tuned on the Common Voice 11.0 Russian dataset based on OpenAI Whisper-base
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Russian speech recognition#Low word error rate#Common Voice fine-tuning
Downloads 15
Release Time : 12/3/2023

Model Overview

This is an automatic speech recognition (ASR) model optimized for Russian, capable of converting Russian speech into text

Model Features

Russian optimization
Fine-tuned on the Common Voice Russian dataset, optimized for Russian speech recognition
Efficient performance
Word error rate (WER) of 25.19%, performing well on Russian speech recognition tasks
Based on Whisper architecture
Utilizes OpenAI Whisper's advanced speech recognition architecture

Model Capabilities

Russian speech recognition
Speech-to-text
Automatic speech transcription

Use Cases

Speech transcription
Russian meeting minutes
Automatically convert Russian meeting recordings into text transcripts
25.19% word error rate
Voice assistant
Speech recognition component for Russian voice assistant applications
Media processing
Russian video subtitle generation
Automatically generate subtitles for Russian video content
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