Sherpa

by k2-fsa

Production server for k2/icefall + Whisper models (PyTorch).

Looking at Sherpa? Try this first.

Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min

TL;DR

Best for gPU streaming server using PyTorch icefall checkpoints. Pricing: free.

Category
Open source
License
Apache-2.0
Stars
★ 971
Last push
2026-08-08
Pricing
free
Platforms
Linux, macOS, Docker

What it is

Reference deployment runtime for icefall models. Apache-2.0.

Best for: GPU streaming server using PyTorch icefall checkpoints.
Watch out for: Replaced for most edge cases by sherpa-onnx / sherpa-ncnn.

Install / use

pip install k2-sherpa

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeYes
Languages supported40
HIPAA eligibleNo

Links

GitHub repo ↗

Sherpa vs Whipscribe

FeatureSherpaWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
Speaker diarizationNoYes
Word timestampsYesYes
StreamingYesNo
Languages4099
PlatformsLinux, macOS, DockerWeb, API, MCP

Alternatives to Sherpa

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 107.0k
whisper.cpp
Georgi Gerganov

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

OSS · MIT ★ 52.8k
faster-whisper
SYSTRAN

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

OSS · MIT ★ 24.8k

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.