Indonesian speech to text: older-model figure

By the Potok teamUpdated ~2 min read

Indonesian speech to text with Potok is a recommended language. The published figure is a word error rate of 7.1 from the earlier large-v2 model, and a third party gave a turbo average of 6.98. These are other people's tests, not our measurements.

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

  • No large-v3 figure was found, so the 7.1 describes the older model.
  • A third-party turbo average of 6.98 points the same way, which adds some confidence.
  • Formal and casual Indonesian differ in word choice, so the register of your speaker matters.
  • Speakers often switch between Indonesian and a regional language mid-sentence.
  • A word error rate counts words that differ from a human reference text.

What a transcript looks like

Sample sentence in Indonesian
[00:00] Speaker 1: Mari kita mulai rapat. Pertama, kita tinjau hasil minggu lalu, lalu kita rencanakan langkah berikutnya.

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
Indonesian (Bahasa Indonesia)Recommendedword error rate 7.1% (large-v2, FLEURS)
Whisper paper, TheWhisper benchmark
Published tests show a low error rate for this language.
No large-v3 figure was found; the figure is from the earlier large-v2 model, and a third party published a turbo average of 6.98.

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. Note the register. News reading and everyday chat differ in word choice, so remember which kind of speech you have before judging the output.
  2. Send the file. Open @potok_now_bot in Telegram and attach audio, video or a voice message, or paste a YouTube link.
  3. Look for language switches. Find passages where the speaker moves into a regional language or into English and check those first.
  4. Send large files through Upload. Up to 2 GB is accepted, and the Upload button of the mini app is the route for the biggest recordings.
  5. Export what you need. TXT or DOCX for notes, SRT or VTT when you want captions with timestamps.
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 7.1 as a result for the newest modelIt comes from the older large-v2 model, which may differ from what runs today.Say that the figure is from an older model.
Ignoring casual speechSlang and shortened words are harder to write down than formal speech.Test a sample of the real conversation.
Missing mid-sentence language switchesRegional words are guessed and may be written oddly.Check those passages against the audio.
Quoting the numbers as our ownThey were published by others.Cite them as other people's tests.

More

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

Frequently asked questions

What is the Indonesian score?

A word error rate of 7.1 from published tests of the large-v2 model, not from our own checks.

Is there a newer figure?

No large-v3 result was found, so the older figure is the one cited on this page.

What about the turbo variant?

A third party published a turbo average of 6.98, which points the same way as the older figure.

What is the largest file I can send?

Files up to 2 GB are accepted, with the Upload button for big recordings.

Is the text translated into English?

No. The transcript stays in Indonesian because the bot does not translate.

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. Whisper speech recognition system (Wikipedia), Wikipedia · checked
  3. Whisper paper, Table 13 (large-v2 on FLEURS) · checked
  4. TheWhisper benchmark (turbo, average over FLEURS, MLS, Common Voice) · 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