AIbase
EN
Home
Whisper Large Persian
W

Whisper Large Persian

Developed by steja
Persian automatic speech recognition model based on Whisper architecture, fine-tuned on Common Voice 11.0 Persian dataset
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Persian speech recognition#Multi-GPU fine-tuning#Low word error rate
Downloads 800
Release Time : 12/21/2022

Model Overview

This is an automatic speech recognition (ASR) model optimized for Persian, fine-tuned based on Whisper-large-v2 architecture, specifically designed for converting Persian speech to text.

Model Features

Persian optimization
Specially fine-tuned for Persian speech recognition, achieving a 26.37% word error rate on Persian test sets
Based on Whisper architecture
Leverages the powerful base architecture of OpenAI Whisper-large-v2 for fine-tuning
Multi-GPU training
Uses multi-GPU distributed training to improve training efficiency

Model Capabilities

Persian speech recognition
Speech-to-text

Use Cases

Speech transcription
Persian speech transcription
Convert Persian speech content to text
Word error rate 26.37%
Voice assistant
Persian voice command recognition
For Persian voice assistants or command control systems
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