Swedish transcription: output and formats

By the Potok teamUpdated ~2 min read

Potok transcribes Swedish voice notes, audio and video in Telegram and returns Swedish text. Published tests of large-v3 report a word error rate of 7.88, which falls in the recommended group. A file may be up to 2 GB, and you can export six formats.

Transcribe a recording

Send your voice message, audio or video to @potok_now_bot on Telegram and the text comes back in the chat.

Open @potok_now_bot in Telegram

Files up to 2 GB · export to TXT, MD, DOCX, PDF, SRT and VTT · speaker labels and timestamps · about 30 languages

Key facts

  • The 7.88 is a word error rate from others' published large-v3 tests, not from our own work.
  • Swedish has three letters beyond the basic Latin set: a with ring, a with two dots and o with two dots.
  • Compound nouns are written as one word, so a split in the output is worth a second look.
  • Subtitle exports use SRT or VTT; both carry times for each line.

What a transcript looks like

Sample sentence in Swedish
[00:00] Speaker 1: Låt oss börja mötet. Först går vi igenom förra veckans resultat, sedan planerar vi nästa steg.

Meaning in English: Let's start the meeting. First, we'll review last week's results, then plan the next steps.

Written by us to show the script and the layout of a transcript. It is not the output of the recognition engine.

Published quality

Quality for this language
LanguageVerdictPublished resultNotes
Swedish (Svenska)Recommendedword error rate 7.88% (large-v3, FLEURS)
Canary-1B-v2 paper
Published tests show a low error rate for this language.

These numbers come from published tests by other people, not from tests by Potok. Your own audio, with its noise, accents and microphone, will differ.

How to do it

  1. Send the clip. Post it to @potok_now_bot; a forwarded voice message works too.
  2. Add labels for interviews. Numbered labels show where the speaker changes.
  3. Add times for citations. They let a reader jump to the right place in the audio.
  4. Check compounds. Look at long words that may have been split into two.
  5. Export subtitles or text. SRT and VTT for video; TXT, MD, DOCX and PDF for documents. Use Upload for files near 2 GB.
What Potok can do
FeatureDetails
Where it worksTelegram bot @potok_now_bot; large files go through the bot's mini app
File sizeUp to 2 GB
ExportTXT, MD, DOCX, PDF, SRT, VTT
Speakers and timeSpeaker labels and timestamps can be switched on
LanguagesAbout 30 languages with good published results; a few more with warnings
TranslationThe transcript is not translated into another language
DictationA separate Potok desktop app lets you dictate text into any program; it recognises Russian speech

Common mistakes

Common mistakes and how to fix them
MistakeWhat happensFix
Replacing the extra letters with plain onesWords change meaning, and a search for the proper spelling fails.Keep the Swedish letters throughout.
Splitting compounds to fit subtitle linesIt reads as an error.Break lines between words instead.
Quoting a year-old figure as a current oneThe model behind it may not be the one in use.State the model name, large-v3.
Waiting for English textNothing arrives, because the bot does not translate.Translate elsewhere if needed.

More

See the full list of languages, the tools and the glossary.

Frequently asked questions

What do I get after sending Swedish audio?

Swedish text in the chat, or a file if it is long, with labels and times if you asked for them.

Is 7.88 good?

It is a low published word error rate, so Swedish is in the recommended group, but it is not a promise for your audio.

Are the special letters kept?

Yes, the output uses the standard Swedish letters.

Can I export a Word document?

Yes, DOCX is one of the six formats.

Does the bot translate Swedish speech?

No, the transcript stays in Swedish exactly as the speakers said it.

Sources

Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.

  1. Word error rate (Wikipedia), Wikipedia · checked
  2. FLEURS speech dataset (Google, Hugging Face), Hugging Face · checked
  3. Canary-1B-v2 paper, Table 11 (Whisper large-v3 on FLEURS) · checked

Try it on your own recording

Send your voice message, audio or video to @potok_now_bot on Telegram and the text comes back in the chat.

Open @potok_now_bot in Telegram