Thai
Benchmark results on Thai Testset from most common Dataset, Mozilla Common Voice. There are 2 version to take a look and iApp ASR in Thai language produced a better result from each version.
Mozilla Common Voice 16.1 Thai Test Set (Version 1)
Results
Test Set Size: 11,038 test examples
Average Word Error Rate: 1.1086199973229822
Average Word Error Rate (No Space): 0.663164235042163
Test conditions
Unseen dataset
Thai language only
Speaker: Male, Female, Children
Detailed Benchmark Results (in Google Sheets):
https://docs.google.com/spreadsheets/d/1rh6nsw8qsZjDf3M8J9lepgnZHep5cD3rbJVOw-MTvj0/edit?usp=sharing
Mozilla Common Voice 17.0 Thai Test Set (Version 2)
Results
Test Set Size: around 1,500 test examples
Average Accuracy: 98.63%
Response Time: 0.3 seconds (outperformed other vendors up to x5 times faster)
Test conditions
Unseen dataset
Thai language only
Speaker: Male, Female, Children
Detailed Benchmark Results (in Google Sheets):
https://docs.google.com/spreadsheets/d/1GoX6C7IoBED4KRamnRaBEArVtRUCt3UE3dwcKiCWc3c/edit?gid=0#gid=0
Last updated