Free Ukrainian transcription: try a tool on a clip

By the Potok teamUpdated ~2 min read

Free Ukrainian transcription is worth a trial on your own clip. Published tests of others on large-v3, used with Potok, give word error rates between 6.51 and 11.5 for Ukrainian, a wide spread. Try a short sample with names and some mixed-language speech.

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 spread from 6.51 to 11.5 shows that published figures depend heavily on the test set.
  • The numbers are from other people's benchmarks, not our measurements.
  • Speakers often move between Ukrainian and Russian in a single conversation, which is a hard case.
  • Apostrophes and soft signs are small marks that matter.

What a transcript looks like

Sample sentence in Ukrainian
[00:00] Speaker 1: Почнімо нараду. Спочатку розглянемо результати минулого тижня, а потім сплануємо наступні кроки.

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
Ukrainian (Українська)Recommendedword error rate 6.51% (large-v3, FLEURS)
Canary-1B-v2 paper, Whale paper
Published tests show a low error rate for this language.
Published large-v3 results range from 6.51 to 11.5.

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. Pick a typical clip. Choose a minute that has names, places and, if realistic, a few words from another language.
  2. Open the bot. Open @potok_now_bot in Telegram and send the clip as a voice message, an audio file or a video.
  3. Check the apostrophe. Look at words where it appears and confirm it was kept.
  4. Mark mixed-language places. See whether foreign words stayed in their own spelling.
  5. Export a copy. Save TXT, DOCX, PDF, SRT or VTT. Files up to 2 GB are accepted.
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
Using the lowest figure as a promiseIt is the best case on one test set.Look at the whole range.
Ignoring language switchesOne foreign phrase can derail a sentence.Test a clip with a switch.
Missing the apostropheIt changes the word.Search for it.
Reading without audioPlausible words hide errors.Listen while reading.
Sending a clip with overlapping voicesTwo speakers at once is the hardest case and teaches little about normal use.Start with one voice at a time, then try overlap on purpose.

More

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

Frequently asked questions

Why two numbers for Ukrainian?

Published results differ by test set, from 6.51 up to 11.5 on large-v3.

Which should I trust?

Neither on its own; test your own sample.

Are they your measurements?

No. They come from published tests of others.

Should I test more than one clip?

Yes. One calm clip and one lively conversation show the range better than a single sample can.

Can I get English text?

No. The transcript stays in the language of the recording.

What is the file size limit?

Files up to 2 GB are accepted, and a long result arrives as a file you can save.

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
  4. Whale paper, Table 5 (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