Burmese speech-to-text
Returns nothingWhisper Large v3 lists Burmese, but on this endpoint 28 of 30 test clips came back as empty transcripts. We do not recommend it for Burmese; this page documents what we found.
Measured accuracy
| Model | Word error rate | Character error rate | Clips with no errors | Empty transcripts | Speed |
|---|---|---|---|---|---|
Whisper Large v3openai/whisper-large-v3 | over 100% | 100% | 0 of 30 | 28 of 30 | 0.098× real time |
Returns nothing. The model lists this language, but our test clips came back as empty transcripts. Scored on characters. The clips are clean, single-speaker read speech, so treat this as a best case for your own recordings. How we measured, and all 83 languages.
What a transcript looks like
The clip with the median error rate from the test, reference text against what the API returned.
| Spoken | သေချာမသိသော်လည်း ၎င်းတွင် ခွပုံစံဖြစ်နေသောလျှာ ပါရှိနိုင်ပါသည်။ ၎င်း၏အစားအစာများတွင် လိပ်များ၊ ငါးကြီးများ၊ အခြားသော မိုဆာဆောငါးကြီးများ ပါဝင်ပြီး၊ ၎င်းသည် လူသားစားသည့်အရာပင် ဖြစ်နိုင်ပါသည်။ |
| Whisper Large v3 | (empty transcript) |
Language detection
All 10 clips we sent without a language field were identified as Burmese. Auto-detection is safe here; sending language=my still skips the detection step.
What to do instead
We would rather you know this before you build than after. For Burmese, look at services that train specifically on the language, such as Google Cloud Speech-to-Text or Azure AI Speech, both of which publish their language lists, or a Whisper checkpoint fine-tuned on Burmese from Hugging Face run on your own hardware. If your audio mixes Burmese with a well-supported language, the well-supported parts will still transcribe. You can confirm all of this on your own audio with the free credit on a new account: transcription playground.
FAQ
How accurate is Whisper for Burmese?
On this endpoint it is not usable: 28 of 30 Burmese test clips came back as empty transcripts.
Does language auto-detection work for Burmese?
In our test, yes: all 10 clips sent without a language were identified as Burmese. Sending language=my still saves the detection step on every request.
Can it translate Burmese speech to English?
The API returns Burmese text. For English, transcribe first and translate the text with a chat model on the same key; with accuracy this low the translation will inherit the errors.