Datasets
Dataset
Indic_ASR_Eval
by ayush-shunyalabs
Indic ASR Eval A curated evaluation set for Indic-language automatic speech recognition. 100 samples are sampled (seed = 42) from each (source dataset × language) cell of seven public Indic ASR corpora.
CC-BY-4.0automatic-speech-recognition 75 11K < n < 10K rows
published 23 Apr 2026
Preview
First 5 rows of commonvoice / test, from the Hugging Face dataset viewer.
| audio | transcript | language | duration | dataset |
|---|---|---|---|---|
| [{"src":"https://datasets-server.huggingface.co/assets/ayush-shunyalabs/Indic_ASR_Eval/--/7c1d7dde6aee30d98075522bc9ec9eb26898f6ab/--/commonvoice/test/0/audio/audio.wav?Expires=1788307911&Signature=IBOQLsHjmNjnvKBLjYUmCIn6enbH2fG8tcBU8taJxUwZqgpx~QJcnTkJMxxzFgEXmFJv-LbV703-sOSq64uRPiNZ9NoaNBjg3Ru3Z… | ভারতের হিন্দি সঙ্গীত জগতে তিনি জগমোহন নামে পরিচিত | Bengali | 6.084000110626221 | commonvoice |
| [{"src":"https://datasets-server.huggingface.co/assets/ayush-shunyalabs/Indic_ASR_Eval/--/7c1d7dde6aee30d98075522bc9ec9eb26898f6ab/--/commonvoice/test/1/audio/audio.wav?Expires=1788307911&Signature=WmtD6798GG-cycVk3UduSK-Vaqf1Pjin85Y2lJ5PCcLv4z45Xxko4mEvOcm7q6GpFjzIMMewJfIGXLMsrIlNtlNpj3auYXXIYb4Bn… | এইচআইভি ভাইরাস মোটামুটি তিন প্রকারের ছড়াতে সক্ষম | Bengali | 4.427999973297119 | commonvoice |
| [{"src":"https://datasets-server.huggingface.co/assets/ayush-shunyalabs/Indic_ASR_Eval/--/7c1d7dde6aee30d98075522bc9ec9eb26898f6ab/--/commonvoice/test/2/audio/audio.wav?Expires=1788307911&Signature=fI6RtJUgyjY6odkp4JERKCq7oSDY3zigRxO1qesSHVjEofK6rn2PZXGkAZJ9bOaNX-Fs3~y2-ljVsTpnBsgH4MwuhqUfH1n-aebjd… | যেসব ভাষা বা ভাষা পরিবার বিশ্বে ব্যাপক অঞ্চল জুড়ে ছড়িয়ে আছে সেগুলিতে এই ব্যাপারটি খুবই সাধারণ | Bengali | 8.13599967956543 | commonvoice |
| [{"src":"https://datasets-server.huggingface.co/assets/ayush-shunyalabs/Indic_ASR_Eval/--/7c1d7dde6aee30d98075522bc9ec9eb26898f6ab/--/commonvoice/test/3/audio/audio.wav?Expires=1788307911&Signature=fsVAL6kpeZAuieC~Fu-VMKN7Sf4AB7mwrFx3z1uulFg3GL7KwK1HevLF57fxqgtYJ~iBmY4TbZ~55nk04~fpWSEuPICjSqF2Fncg6… | ইমন সাহা একটি গানের সুর ও সঙ্গীত প্রযোজনা করেছেন | Bengali | 5.21999979019165 | commonvoice |
| [{"src":"https://datasets-server.huggingface.co/assets/ayush-shunyalabs/Indic_ASR_Eval/--/7c1d7dde6aee30d98075522bc9ec9eb26898f6ab/--/commonvoice/test/4/audio/audio.wav?Expires=1788307911&Signature=MujepMnBeOzbX5HyktXGptseMqNe6x-rk24R4C0tp43Zt5xXVjAJ2KsCRFTo3jDO-X2u9dbDH2BjH5E9fvMiSfyUPM4Mx-mnFzwa3… | অধিকাংশ সময়েই টম গডার্ডের সাথে বোলিং আক্রমণে নামতেন | Bengali | 6.480000019073486 | commonvoice |
Cite this
CC-BY-4.0audiotextCite
Tags
task_categories:automatic-speech-recognitionlanguage:bnlanguage:gulanguage:hilanguage:knlanguage:mllanguage:mrlanguage:orlanguage:palanguage:salanguage:talanguage:telanguage:urlanguage:bholanguage:mailicense:cc-by-4.0size_categories:1K<n<10Kformat:parquetmodality:audiomodality:textlibrary:datasetslibrary:pandaslibrary:polarslibrary:mlcroissantregion:usindicspeechasrevaluationbenchmark