Russian Open STT

by Silero

20kh Russian ASR corpus — the largest open Russian-language speech dataset.

TL;DR

20kh Russian ASR corpus — the largest open Russian-language speech dataset.

Best for russian ASR training and evaluation at scale. Pricing: free.

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

What it is

Open STT (Silero) is a 20k-hour Russian ASR corpus assembled from YouTube + audiobooks + public speech + radio. License: CC BY-NC 4.0.

Best for: Russian ASR training and evaluation at scale.
Watch out for: CC BY-NC 4.0 · NON-COMMERCIAL · multiple subsets (audiobooks, YouTube, public speech). Cite: Veysov, 2019.

Install / use

git clone https://github.com/snakers4/open_stt

Features

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

Russian Open STT vs Whipscribe

FeatureRussian Open STTWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsNoYes
StreamingNoNo
Languages199
PlatformsGitHubWeb, API, MCP

Alternatives to Russian Open STT

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.