Benchmark
The cost of a Benchmarking job depends on the size of the sample dataset used for evaluation, the number of machine translation services that are compared, ...
Wed, 13 Jul, 2022 at 12:04 PM
Benchmark is one of the main experiences at aiXplain, which means it resides in the Navigation Bar located on the top left side of your screen under “BENCHM...
Mon, 14 Nov, 2022 at 8:19 PM
Benchmark is a tool provided by aiXplain to measure and compare the quality of outputs generated by one or more selected models using reference-based benchm...
Mon, 14 Nov, 2022 at 8:17 PM
Benchmarking can be directly accessed on platform.aixplain.com from the main site navigation menu by clicking on “BENCHMARK”. Benchmarking can als...
Mon, 14 Nov, 2022 at 8:20 PM
If you could not find the right language pair for your MT project in the Benchmarking experience nor in the Discovery experience, please feel free to reques...
Fri, 21 Jan, 2022 at 3:37 AM
Here’s what you need to know before uploading your own dataset: Upload file format You should be sure that the files you upload are correctly for...
Tue, 28 Jun, 2022 at 6:41 AM
Reference similarity metrics: These metrics measure the similarity between reference translations and machine translation output, with higher similarity lea...
Tue, 29 Mar, 2022 at 6:41 AM
Below are the Metric Details for ASR Benchmarking: Word Error Rate (WER) Summary: Computes the number of word errors (insertions, deletions, ...
Tue, 29 Mar, 2022 at 6:40 AM
Yes, we provide publicly available datasets, our own selection of aiXplain datasets and such datasets that are shared by other aiXplain community members. D...
Fri, 21 Jan, 2022 at 3:40 AM
Benchmarking jobs call each selected service to collect translations (usage fees apply) for text samples provided in the selected dataset(s). While doing th...
Wed, 13 Jul, 2022 at 12:19 PM