HuggingFace PEFT

by Hugging Face

LoRA / adapters for parameter-efficient Whisper fine-tuning.

TL;DR

LoRA / adapters for parameter-efficient Whisper fine-tuning.

Best for domain-adapting Whisper on a single GPU without full fine-tuning. Pricing: free.

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

What it is

PEFT implements LoRA, IA3, prefix-tuning, and more. The community standard for cheap Whisper adaptation. Apache-2.0.

Best for: Domain-adapting Whisper on a single GPU without full fine-tuning.
Watch out for: Adapter formats not standardized across all backends.

Install / use

pip install peft

Features

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

HuggingFace PEFT vs Whipscribe

FeatureHuggingFace PEFTWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages10099
PlatformsLinuxWeb, API, MCP

Alternatives to HuggingFace PEFT

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.