Whisper-large-v2-kazakh Open-source Speech Recognition Model - Accurately Recognize Kazakh Speech Content

Whisper Large V2 Kazakh

Developed by DrishtiSharma

This model is a fine-tuned speech recognition model based on OpenAI's Whisper Large V2 on the Kazakh Common Voice 11.0 dataset

Speech Recognition

Transformers

OtherOpen Source License:Apache-2.0 #Kazakh speech recognition #Multilingual support #Low word error rate

Downloads 40

Release Time : 12/20/2022

Model Overview

An automatic speech recognition (ASR) model optimized for Kazakh, achieving a 34.7% word error rate on the Common Voice 11.0 Kazakh test set

Model Features

Kazakh optimization

Specially fine-tuned for Kazakh speech recognition tasks

Based on Whisper architecture

Utilizes the powerful speech recognition architecture of OpenAI Whisper Large V2

Open-source license

Uses Apache 2.0 license, allowing for commercial and research use

Model Capabilities

Kazakh speech recognition

Speech-to-text

Use Cases

Speech transcription

Kazakh speech transcription

Convert Kazakh speech content into text

Achieved a 34.7% word error rate on the test set

Voice assistant

Kazakh voice command recognition

Used for developing Kazakh voice assistants and control systems

Training Loss	Epoch	Step	Validation Loss	Wer
0.0017	7.0	700	0.4261	34.7012

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Whisper Large V2 Kazakh

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 Whisper Large V2 Kazakh - Drishti Sharma

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

🔧 Technical Details

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License