Skip to content

Klang · Transcription

Klang Pianissimo

KlangTranscriptionOpen weights. The weights are publicly available in a Hugging Face repo.
From Eurouter's listing:
Klang Pianissimo is Klang's open-weight Swedish speech-to-text model, a 600M-parameter fine-tune of NVIDIA Parakeet TDT 0.6B v3 with punctuation, capitalization and word-level timestamps, built for fast transcription of short clips and long recordings.
Max context
1
Listings
1
Providers
1

Evidence and sources

🤗 KlangAI/pianissimo-svReleased 23 Sep 2026
Sources: EURouter data, llminfo researchPrimary data from EURouter from llminfo research: release date
Tags from its sources:open-sourceaudiotranscriptionspeech-to-textswedish

Advantages and trade-offs

Compared with 10 representative transcription models

Advantages

Open weights available

The weights are public. None of its peers say whether theirs are.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Audio
Text

Capabilities

Supported operations and provider-stated features

Structured output

Listings

 Eurouterpianissimo-svSource: EURouter data1

Benchmarks

No benchmark scores yet.

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works