Hindi speech to text: a real sample transcript

Hindi (हिन्दी), 27 seconds, taken 2026-10-27. Sentences read aloud by a volunteer. Output of the free preview with the language set to Hindi, not corrected.

The transcript, as the engine returned it

1. 0:00कल यहां साथ बजे आना ना भूलना
2. 0:03स्पेन के खिलाफ हेट्रिक के साथ रुनाल्टो नी बनाया लेया रिकोर्ट
3. 0:11इंटिया तुटे कोंख्लेव में दीपिका नी बताया कामयाबी का मंद्र लगाई थूंके
4. 0:18अवीसी की केंद्रिये सुची में सन शोदन का प्रस्ताव मंजूर

Download this transcript as SRT (written by the same exporter the app uses; the other formats are TXT, timestamped TXT, VTT, Markdown, JSON and CSV).

Against the reference sentences

Word error rate 51.3% (20 edits over 39 words), character error rate 15.3%; normalisation: plain (explained on the samples page).

The sentences the speaker was asked to read:

1. कल यहाँ सात बजे आना न भूलना।
2. स्पेन के खिलाफ हैट्रिक के साथ रोनाल्डो ने बनाया नया रिकॉर्ड
3. इंडिया टुडे कॉन्क्लेव में दीपिका ने बताया कामयाबी का मंत्र, लगाए ठुमके
4. ओबीसी की केंद्रीय सूची में संशोधन का प्रस्ताव मंजूर

Where the recording comes from

• ·Source: Mozilla Common Voice 22.0, test split (CC0 1.0 public domain dedication, https://commonvoice.mozilla.org/en/datasets, https://creativecommons.org/publicdomain/zero/1.0/; copy used: https://huggingface.co/datasets/fsicoli/common_voice_22_0, whose card also says cc0-1.0).
• ·Licence: CC0 1.0 (creativecommons.org/publicdomain/zero/1.0/).
• ·Which recording: One volunteer speaker (no profile details given): the speaker with the most clips in the part of the test archive we read, their clips in the test file's order that are 2.5 to 7 seconds long and have no down-votes, until about 24 seconds were collected. Chosen by that rule, not by how well the engine did.
• ·Clip ids: common_voice_hi_25154266, common_voice_hi_25154267, common_voice_hi_25154268, common_voice_hi_25154269.

How every sample was made, step by step, is on the samples page. To try your own Hindi recording, use the Hindi transcription page.