Free Finnish transcription: check a tool on a short clip

By the Potok teamUpdated ~2 min read

To check a free Finnish transcription tool, send a clip with long compound words and read how each one was written. In published tests of large-v3, Finnish scores a word error rate of 7.7, and Potok reports that as someone else's result.

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 7.7 is a word error rate for large-v3 in a published test, not our measurement.
  • Finnish builds long words with endings, so one wrong letter makes a whole word count as wrong.
  • Word error rate therefore punishes small slips in Finnish more than in short-word languages.
  • The transcript stays in Finnish and is not translated.

What a transcript looks like

Sample sentence in Finnish
[00:00] Speaker 1: Aloitetaan kokous. Ensin käymme läpi viime viikon tulokset ja sitten suunnittelemme seuraavat vaiheet.

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
Finnish (Suomi)Recommendedword error rate 7.7% (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. Gather long words. Use a clip where the speaker says place names, job titles and other long words with endings.
  2. Open the bot. Open @potok_now_bot in Telegram and send the clip as a voice message or an audio file.
  3. Read the long words letter by letter. Compare each against the speaker. A single wrong ending is an error.
  4. Check double letters. Finnish has long and short sounds, written with doubled letters. See whether they come through.
  5. Send the full file. Up to 2 GB is accepted, with the Upload button for large files. Export TXT or DOCX.
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
Counting a near miss as a hitOne wrong ending still makes the word wrong.Be strict when you mark errors.
Ignoring doubled lettersA missing double letter changes the word.Scan for them in the output.
Comparing with a language of short wordsScores are not comparable across languages.Compare tools on Finnish only.
Testing with a single sentenceIt may avoid the hard words.Use a full minute of natural speech.

More

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

Frequently asked questions

How does Finnish score?

Published large-v3 results show a word error rate of 7.7, which is in the good range.

Why does word error rate bite harder in Finnish?

Long words carry many endings, so a tiny slip makes a whole word wrong.

Is a video file fine?

Yes, video, audio, voice messages and YouTube links all work within the 2 GB limit.

Can I export to Word?

Yes. DOCX is among the formats, alongside TXT, MD, PDF, SRT and VTT.

Will I get a translated version?

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

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