Intel Extension for PyTorch (IPEX)

by Intel

BF16/AMX speedups for Whisper PyTorch inference on Intel CPUs.

TL;DR

BF16/AMX speedups for Whisper PyTorch inference on Intel CPUs.

Best for whisper on Xeon servers with AMX or AVX-512. Pricing: free.

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

What it is

Drop-in PyTorch extension delivering Intel-specific optimizations. Apache-2.0.

Best for: Whisper on Xeon servers with AMX or AVX-512.
Watch out for: Most useful only on Intel CPUs with AMX.

Install / use

pip install intel-extension-for-pytorch

Features

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

Intel Extension for PyTorch (IPEX) vs Whipscribe

FeatureIntel Extension for PyTorch (IPEX)Whipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsLinuxWeb, API, MCP

Alternatives to Intel Extension for PyTorch (IPEX)

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.