Appen Inc. and DataoceanAI have provided new high-quality English ASR datasets for scripted and conversational speech across multiple accents, raising questions about model evaluation and potential risks of benchmarking.
New high-quality, private datasets How can I evaluate my model on this data? Do models trained on the data providers have an advantage?
TLDR : Appen Inc. and DataoceanAI have provided high-quality English ASR datasets covering scripted and conversational speech over multiple accents. To prevent potential risks of benchmaxxing or test-set contamination, we will keep these datasets private for a high-quality measu…
To this end, we have worked with Appen Inc. and DataoceanAI to curate high-quality datasets for ASR benchmarking.
