CDLI non-standard speech ASR models
Collection
8 items • Updated • 1
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Trained on CDLI's non-standard speech dataset (Ugandan English): cdli/ugandan_english_nonstandard_speech_v1.0
Performance on test set before and after:
before: WER on test: 0.62
after: WER on test: 0.34
More details: https://www.cdl-inclusion.com