Vietnamese transcription at Potok returns text with tone marks. The published word error rate is 10.3 for the earlier large-v2 model, while another test set gave 18.9 for large-v3, so results vary with the data. Files up to 2 GB are accepted in Telegram.
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 10.3 is a word error rate from published tests by others, not our own measurement.
- Another published test gave 18.9 for large-v3, so the spread between data sets is wide.
- Vietnamese uses the Latin alphabet with tone marks and extra vowel signs, and every syllable is separated by a space.
- Timestamps and numbered speaker labels are optional.
What a transcript looks like
[00:00] Speaker 1: Chúng ta bắt đầu cuộc họp nhé. Trước tiên, chúng ta sẽ xem lại kết quả tuần trước, sau đó lên kế hoạch cho các bước tiếp theo.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
| Language | Verdict | Published result | Notes |
|---|---|---|---|
| Vietnamese (Tiếng Việt) | Recommended | word error rate 10.3% (large-v2, FLEURS) Whisper paper | Published tests show a low error rate for this language. The figure is from the earlier large-v2 model; another test set gave 18.9 for large-v3, so results vary with the data. |
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
- Choose a clip. Pick a short piece with clear speech and send it to @potok_now_bot.
- Compare it with the audio. Judge whether the quality suits your own recordings, which may sit nearer 10 or 19.
- Send the whole file. Up to 2 GB goes in, with the Upload button of the mini app for the largest.
- Turn on labels and times. Both help with meetings and long interviews.
- Check tone marks. A wrong mark makes a different syllable, so read names and numbers closely.
- Export. TXT, MD, DOCX, PDF, SRT or VTT.
| Feature | Details |
|---|---|
| Where it works | Telegram bot @potok_now_bot; large files go through the bot's mini app |
| File size | Up to 2 GB |
| Export | TXT, MD, DOCX, PDF, SRT, VTT |
| Speakers and time | Speaker labels and timestamps can be switched on |
| Languages | About 30 languages with good published results; a few more with warnings |
| Translation | The transcript is not translated into another language |
| Dictation | A separate Potok desktop app lets you dictate text into any program; it recognises Russian speech |
Common mistakes
| Mistake | What happens | Fix |
|---|---|---|
| Trusting one number for every recording | Published tests ranged from 10.3 to 18.9. | Test your own audio. |
| Searching without the marks | Words that differ only by a mark are not found together. | Search with the exact marks. |
| Treating spaces as word boundaries | A multi-syllable word is split into pieces. | Review compounds in context. |
| Waiting for an English transcript | The bot does not translate. | Translate the text elsewhere if you need to. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Does the transcript include tone marks?
Yes, it is written Vietnamese with its tone marks and vowel signs, so the display font should support them.
Why do the published numbers differ?
One test of large-v2 gave 10.3 and another of large-v3 gave 18.9, because the data sets differ.
Can I get subtitles?
Yes. Export SRT or VTT and check line breaks.
Does the bot separate speakers?
It can mark turns with numbered labels once you enable them.
What is the size limit?
Files up to 2 GB; use Upload in the mini app for the largest.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- Word error rate (Wikipedia), Wikipedia · checked
- FLEURS speech dataset (Google, Hugging Face), Hugging Face · checked
- 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