Skip to page content
SAVRN
Search Plan a project

Dataset · Speech recognition

nepali-english-codemix-asr-test-outputs

by AI Lab Pvt Ltd ailabpvtltd/nepali-english-codemix-asr-test-outputs

Released by AI Lab Pvt. Ltd., Nepal. Text only: no audio is included. For every clip of our Nepali–English code-mixed test set (4,610 clips, 9.1 h) and of the FLEURS Nepali test set (586 digit-free clips), this dataset gives the reference transcript and the…

Rows5,196
Configurations2
Size3.3 MB
Licenseother
AccessPublicly accessible
Monthly Downloads—

Dataset Card

Released by AI Lab Pvt. Ltd., Nepal. Text only: no audio is included. For every clip of our Nepali–English code-mixed test set (4,610 clips, 9.1 h) and of the FLEURS Nepali test set (586 digit-free clips), this dataset gives the reference transcript and the output of 7 speech recognition systems: SraVaani-1.0 zero-shot and fine-tuned for 6 and 12 epochs, and Whisper large-v3-turbo and IndicConformer, zero-shot and fine-tuned. Use it to inspect errors, compare models clip by clip, or recompute any metric. WER is computed over the whole set (total word errors divided by total reference words) on the normalised text. FLEURS writes English loanwords in Devanagari while our models write them in…

Excerpt from the card by AI Lab Pvt Ltd, licensed other.

Structure

fleurs 586 rows

SplitRowsSize
train5861.5 MB
idlarge_stringfleurs_filelarge_stringdomainlarge_stringduration_sfloat64referencelarge_stringreference_codemixedlarge_stringsravaani_zeroshotlarge_stringsravaani_finetuned_6eplarge_stringsravaani_finetuned_12eplarge_stringwhisper_zeroshotlarge_stringwhisper_finetunedlarge_stringindicconformer_zeroshotlarge_stringindicconformer_finetunedlarge_string

test 4,610 rows

SplitRowsSize
train4,6107.3 MB
idlarge_stringdomainlarge_stringduration_sfloat64source_had_numbersboolhas_englishboolreferencelarge_stringsravaani_zeroshotlarge_stringsravaani_finetuned_6eplarge_stringsravaani_finetuned_12eplarge_stringwhisper_zeroshotlarge_stringwhisper_finetunedlarge_stringindicconformer_zeroshotlarge_stringindicconformer_finetunedlarge_string

Details

Repository
ailabpvtltd/nepali-english-codemix-asr-test-outputs
Publisher
AI Lab Pvt Ltd
Task category
Speech recognition
Tags
code-switching, code-mixing, nepali
Size category
1K<n<10K
Languages
ne, en
Revision
a2ed36a7264b6b1951461e6f9bf39f4dc9115367
Last updated
2026-10-15

Files

5 files, 3.3 MB in total.

Data3 files · 3.3 MB
Documentation1 file · 7.0 KB
Repository1 file · 2.5 KB
Every file
FileTypeSizeSHA-256
data/fleurs.parquetData625.5 KBde62b227e967
data/test.parquetData2.7 MB81bb08d8c60b
results.csvData1.8 KB—
README.mdDocumentation7.0 KB—
.gitattributesRepository2.5 KB—

License and Download

License
other
Access
No access gate
Download from AI Lab Pvt Ltd

Released by AI Lab Pvt Ltd through its official repository on Hugging Face.