MASR (Mandarin Streaming ASR)

by yeyupiaoling

Streaming Conformer + DeepSpeech2 in PyTorch for Mandarin.

TL;DR

Streaming Conformer + DeepSpeech2 in PyTorch for Mandarin.

Best for mandarin Conformer baselines reproducible from scratch. Pricing: free.

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

What it is

A PyTorch streaming ASR toolkit focused on Mandarin. Apache-2.0.

Best for: Mandarin Conformer baselines reproducible from scratch.
Watch out for: Documentation primarily Chinese; small community.

Install / use

git clone https://github.com/yeyupiaoling/MASR

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeYes
Languages supported2
HIPAA eligibleNo

MASR (Mandarin Streaming ASR) vs Whipscribe

FeatureMASR (Mandarin Streaming ASR)Whipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingYesNo
Languages299
PlatformsLinuxWeb, API, MCP

Alternatives to MASR (Mandarin Streaming ASR)

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.