Microsoft UniLM

by Microsoft

Home of WavLM, HuBERT++, Speech-T5, BEATs, VALL-E.

TL;DR

Home of WavLM, HuBERT++, Speech-T5, BEATs, VALL-E.

Best for pulling SOTA speech encoder pretrains from Microsoft. Pricing: free.

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

What it is

Microsoft's foundation-models monorepo with several speech research releases. MIT.

Best for: Pulling SOTA speech encoder pretrains from Microsoft.
Watch out for: Mixed licenses per sub-project — some research-only.

Install / use

git clone https://github.com/microsoft/unilm

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported99
HIPAA eligibleNo

Microsoft UniLM vs Whipscribe

FeatureMicrosoft UniLMWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsLinuxWeb, API, MCP

Alternatives to Microsoft UniLM

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.