AIbase
EN
Home
Phowhisper Small
P

Phowhisper Small

Developed by vinai
PhoWhisper is a system specifically designed for Vietnamese automatic speech recognition, fine-tuned based on the Whisper model, supporting various Vietnamese accents.
Speech Recognition
Transformers
 OtherOpen Source License:Bsd-3-clause#Vietnamese speech recognition#Multi-accent adaptation#Whisper fine-tuning
Downloads 2,725
Release Time : 2/18/2024

Model Overview

PhoWhisper is a Vietnamese automatic speech recognition system that achieves state-of-the-art performance on Vietnamese ASR benchmark datasets by fine-tuning the multilingual Whisper model with an 844-hour Vietnamese dataset.

Model Features

Multi-accent support
PhoWhisper is fine-tuned using an 844-hour dataset covering various Vietnamese accents, enabling it to recognize different Vietnamese accents.
High performance
Achieves state-of-the-art performance on Vietnamese ASR benchmark datasets.
Based on Whisper model
Fine-tuned on the multilingual Whisper model, inheriting its robustness and multilingual capabilities.

Model Capabilities

Vietnamese speech recognition
Multi-accent speech recognition

Use Cases

Speech-to-text
Vietnamese speech transcription
Convert Vietnamese speech content into text, suitable for scenarios such as meeting minutes and voice notes.
High-accuracy Vietnamese speech recognition
Voice assistant
Vietnamese voice assistant
Provides voice interaction functionality for Vietnamese users, supporting multiple accents.
Enhances the Vietnamese recognition capability of voice assistants
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase