fairseq2 (via seamless_communication)

by Meta AI

Modular successor to fairseq used by Seamless models.

TL;DR

Modular successor to fairseq used by Seamless models.

Best for pinned fairseq2 environment for SeamlessM4T training/eval. Pricing: free.

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

What it is

Note: fairseq2 ships alongside SeamlessM4T; this repo is the public install path for it.

Best for: Pinned fairseq2 environment for SeamlessM4T training/eval.
Watch out for: Distribution channel — official fairseq2 repo is internal.

Install / use

pip install fairseq2

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported100
HIPAA eligibleNo

fairseq2 (via seamless_communication) vs Whipscribe

Featurefairseq2 (via seamless_communication)Whipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages10099
PlatformsLinuxWeb, API, MCP

Alternatives to fairseq2 (via seamless_communication)

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.