Sindhi speech-to-text
Not usableWe sent 30 Sindhi 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% | over 100% | 0 of 30 | 7 of 30 | 0.161× real time |
Not usable. Most words come out wrong. Do not build on it for this language. Whisper wrote Sindhi in Devanagari; the test references use the Arabic-based Sindhi script, so the character error rate reflects the script as much as the recognition. 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 | صرف ٻن هفتن ۾ آمريڪن ۽ فري فرانسيسي فوجن ڏکڻ فرانس کي آزاد ڪيو ۽ جرمني جو رخ ڪري رهيا هئا. |
| Whisper Large v3 | (empty transcript) |
Language detection
All 10 clips we sent without a language field were identified as Sindhi. Auto-detection is safe here; sending language=sd still skips the detection step.
What to do instead
We would rather you know this before you build than after. For Sindhi, 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 Sindhi from Hugging Face run on your own hardware. If your audio mixes Sindhi 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 Sindhi?
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 Sindhi?
In our test, yes: all 10 clips sent without a language were identified as Sindhi. Sending language=sd still saves the detection step on every request.
Can it translate Sindhi speech to English?
The API returns Sindhi 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.