Bulgarian speech to text: published results

By the Potok teamUpdated ~2 min read

Bulgarian speech to text in Potok is among the languages marked as recommended. Published tests of the large-v3 model give a word error rate of 12.86 for Bulgarian, a figure from other people's work, not our measurement. Send voice notes, audio or video to the Telegram bot.

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

  • 12.86 means roughly one word in eight can differ from a human reference, so a read-through is still needed.
  • Bulgarian is written in the Cyrillic script, and the exported files keep that script as spoken.
  • Only one published source was found for this language, so treat the figure as one data point.
  • The transcript stays in Bulgarian and is not converted into another language.

What a transcript looks like

Sample sentence in Bulgarian
[00:00] Speaker 1: Да започнем срещата. Първо ще прегледаме резултатите от миналата седмица, а след това ще планираме следващите стъпки.

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
Bulgarian (Български)Recommendedword error rate 12.86% (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. Pick the recording. A lecture, interview or voice note works. Trim long silence at the start if you can.
  2. Message the bot. In Telegram open @potok_now_bot and forward or attach the file, or paste a YouTube link.
  3. Large files. Anything up to 2 GB can be sent. For big uploads the Upload button in the bot's mini app is the route.
  4. Wait for the result. A short transcript arrives as a chat message and a long one comes as a file.
  5. Proofread names. Place names, surnames and brand names are where mistakes cluster, so scan those first.
  6. Export. Pick TXT, MD, DOCX, PDF, SRT or VTT depending on whether you need notes or 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 12.86 as a promiseIt is a single published figure and your audio may differ.Read the first page of output before sharing it.
Sending a phone call recorded on a speakerEcho and distance raise the number of wrong words.Record closer to the voice when you can.
Expecting names of speakersThe bot labels voices as Speaker 1, Speaker 2 and so on.Rename them in the exported document.
Pasting the text into subtitles without timestampsYou lose sync with the picture.Export SRT or VTT instead of TXT.

More

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

Frequently asked questions

Is Bulgarian well supported?

It is marked as recommended, based on a published word error rate of 12.86 for the large-v3 model.

Whose tests are these?

They are published by others, not by us, because we did not measure Bulgarian ourselves.

Can I get subtitles?

Yes. Export SRT or VTT with timestamps turned on before you send the file.

What if my recording mixes languages?

Foreign words may be written wrongly or in odd spelling, so check those passages by ear.

Does the bot change Bulgarian into another language?

No. The transcript stays in the language of the recording and is not converted.

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