Shona speech-to-text
Not usableWe sent 30 Shona test clips through this API. Whisper Large v3 made over 100% word errors, which is not good enough to read as a transcript. This page shows what came back so you can judge for yourself.
Measured accuracy
| Model | Word error rate | Character error rate | Clips with no errors | Empty transcripts | Speed |
|---|---|---|---|---|---|
Whisper Large v3openai/whisper-large-v3 | over 100% | 22% | 0 of 30 | 0 of 30 | 0.055× real time |
Not usable. Most words come out wrong. Do not build on it for this language. 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 | Tsvakurudzo yakaitwa mazana makumi maviri emakore apfuura yakaratidza kuti pane zvikamu zviviri zvekusiyana kwemajini: yakavanzwa uye inoratidzwa. |
| Whisper Large v3 | Chakurudzo yaka ituwa maza na makumimaviri e makura afura yaka rateza kutipane jikamu jiviri zhoksiane kwe majini yaka wanzwa uye inoratizwa. |
Language detection
Send language=sn. Of 10 clips sent without it, 9 were identified as Shona; the others were labelled Swahili (1). When detection is wrong, Whisper writes the transcript in the language it guessed.
What to do instead
We would rather you know this before you build than after. For Shona, 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 Shona from Hugging Face run on your own hardware. If your audio mixes Shona 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 Shona?
On 30 clean read-speech clips it made over 100% word errors. Most words come out wrong. Do not build on it for this language. Real recordings with noise, accents or several speakers will score worse.
Does language auto-detection work for Shona?
Mostly. Of 10 clips sent without a language, 9 were identified as Shona; the rest were labelled Swahili (1). A wrong label means the transcript is written in the wrong language, so always send language=sn.
Can it translate Shona speech to English?
The API returns Shona 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.