Malay transcription: a look at the output

By the Potok teamUpdated ~2 min read

Send a Malay recording to Potok on Telegram and the Malay transcription returns as text in the same chat. The published word error rate is 8.7, measured on the earlier large-v2 model because no large-v3 figure was found. Short results arrive as a message, long ones as a file up to 2 GB.

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 8.7 belongs to large-v2 and comes from published tests of others, not from our own measurements.
  • Malay is written in the Latin alphabet, so the text opens in any editor without special fonts.
  • Quoted English words are common in speech and may be written either way in the result.
  • A short transcript lands in the chat as text, a longer one as a file.

What a transcript looks like

Sample sentence in Malay
[00:00] Speaker 1: Mari kita mulakan mesyuarat. Pertama, kita semak keputusan minggu lalu, kemudian kita rancang langkah seterusnya.

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
Malay (Bahasa Melayu)Recommendedword error rate 8.7% (large-v2, FLEURS)
Whisper paper
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.

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. Start with a short clip. Open @potok_now_bot and send one minute of your recording to see the layout.
  2. Decide on labels. For a panel or a call, turn on speaker labels so each turn starts on its own line.
  3. Send the whole file. Files up to 2 GB are accepted. Use the Upload button of the mini app for a long lecture or a big video.
  4. Add timestamps for long material. A time before each paragraph makes it easy to find a quote again.
  5. Export in the form you need. TXT, MD, DOCX and PDF for reading, SRT and VTT for captions.
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 8.7 as a current-model resultThe newer model may behave differently.Say that the figure comes from large-v2.
Mixing up two spellings of one borrowed wordSearch in the document misses half the cases.Pick one spelling and replace the other.
Skipping the namesPlace and personal names are the usual weak spot in any language.Check them against a reliable source.

More

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

Frequently asked questions

What will the Malay transcript look like?

Plain Malay text split into paragraphs, with a speaker label and a time if you switch them on.

Which model does the 8.7 come from?

From large-v2. A figure for large-v3 was not found, so the earlier model is the one cited.

Is the text easy to edit?

Yes. Malay uses the Latin alphabet, and DOCX export opens in any word processor.

Can I use it for captions?

Yes, export SRT or VTT and review the line breaks.

Does the bot turn Malay into another language?

No. The words come back in Malay, and 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

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