VIVOS

by AILAB VNU-HCM

15h Vietnamese read-speech ASR corpus — the open Vietnamese ASR baseline.

TL;DR

15h Vietnamese read-speech ASR corpus — the open Vietnamese ASR baseline.

Best for vietnamese ASR baselines + low-resource Vietnamese research. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
HuggingFace

What it is

VIVOS is a 15-hour Vietnamese ASR corpus from 65 speakers reading newspaper text. The open Vietnamese ASR baseline. License: CC BY-NC-SA 4.0.

Best for: Vietnamese ASR baselines + low-resource Vietnamese research.
Watch out for: CC BY-NC-SA 4.0 · NON-COMMERCIAL · 65 speakers · read newspaper text. Cite: Luong & Vu, 2016.

Install / use

from datasets import load_dataset; ds = load_dataset('AILAB-VNUHCM/vivos')

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supported1
HIPAA eligibleNo

VIVOS vs Whipscribe

FeatureVIVOSWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsNoYes
StreamingNoNo
Languages199
PlatformsHuggingFaceWeb, API, MCP

Alternatives to VIVOS

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.