AIbase
EN
Home
SSL Harveen Chadda Fine Tuning
S

SSL Harveen Chadda Fine Tuning

Developed by rajat99
This model is a fine-tuned speech recognition model based on Harveenchadha/vakyansh-wav2vec2-hindi-him-4200 on an unknown dataset, supporting Hindi and achieving a word error rate of 10.08% on the evaluation set.
Speech Recognition
Transformers
Open Source License:MIT#Hindi Speech Recognition#Low Word Error Rate#Wav2Vec2 Fine-tuning
Downloads 30
Release Time : 4/12/2022

Model Overview

This is a speech recognition model optimized for Hindi, obtained by fine-tuning a pre-trained model, suitable for speech-to-text tasks.

Model Features

Low Word Error Rate
Achieved a word error rate (WER) of 10.08% on the evaluation set, demonstrating excellent performance.
Based on wav2vec2 Architecture
Utilizes the advanced wav2vec2 architecture for speech recognition tasks.
Hindi Optimized
Specifically fine-tuned and optimized for Hindi speech recognition.

Model Capabilities

Hindi Speech Recognition
Speech-to-Text

Use Cases

Speech Transcription
Hindi Meeting Minutes
Automatically convert Hindi meeting recordings into text transcripts
Approximately 90% accuracy
Voice Assistant
Speech recognition module for Hindi voice assistant applications
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