Hungarian transcription: audio and video to text

By the Potok teamUpdated ~2 min read

Hungarian is a borderline language for Potok: it works in the Telegram bot, but the text needs a careful read. Published tests of the large-v3 model give a word error rate of 14.11, close to the cut-off we use for recommended languages. Files up to 2 GB are accepted.

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 14.11 is a published word error rate for large-v3, not a measurement we made.
  • It sits close to our cut-off for recommended languages, so we call Hungarian borderline.
  • Hungarian builds long words by adding endings, so one wrong ending counts as a whole wrong word.
  • The vowels ő and ű, with double acute accents, are easy to lose.

What a transcript looks like

Sample sentence in Hungarian
[00:00] Speaker 1: Kezdjük el az értekezletet. Először átnézzük a múlt heti eredményeket, aztán megtervezzük a következő lépéseket.

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
Hungarian (Magyar)Recommended, borderlineword error rate 14.11% (large-v3, FLEURS)
Canary-1B-v2 paper
Published tests show an error rate close to our 15% line. Check a short sample first.
This figure is close to the 15% line we use, so treat it as borderline.

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. Treat the first run as a test. Send a short clip to @potok_now_bot and read the answer slowly.
  2. Then process the rest. Files up to 2 GB are accepted, and the mini app's Upload button covers the big ones.
  3. Review the endings. Check suffixes on nouns and verbs, because they carry the grammar.
  4. Check the letters. Look for ő, ű, á, é, í, ó, ö, ú and ü, since a plain letter changes the word.
  5. Check names. Hungarian puts the family name first, so make sure the order matches your document.
  6. Export. TXT, MD, DOCX, PDF, SRT or VTT.
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
Treating a borderline score as a clean passErrors are more common than for the best languages.Plan an editing pass.
Replacing ő with ö in a copyThe letters are different and spell-check flags the word.Keep the original characters.
Swapping name orderGiven and family names change places in a form.Follow your document's convention.
Reading a long suffixed word as one wrong letterOne wrong ending changes the grammar of the whole phrase, not just a letter.Read each phrase aloud against the audio before you accept it.

More

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

Frequently asked questions

Why is Hungarian called borderline?

Its published word error rate of 14.11 is close to the line we use to separate recommended languages from the rest.

Can I rely on the transcript?

Use it as a strong draft, and read the text against the audio for names, numbers and endings.

Is Hungarian harder than Finnish for the bot?

Published numbers say so: Finnish shows 7.7 while Hungarian shows 14.11, so Hungarian usually needs more editing after the transcript arrives.

Does it keep the special letters?

It should, but verify ő and ű, which are often replaced by similar letters.

How big may the file be?

Up to 2 GB, with an Upload button in the mini app for large files.

Is Hungarian translated?

No. The text stays Hungarian, because the bot does not translate transcripts into another language.

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