mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-10 02:22:17 +00:00
6c2c9b9d74
* Add recipe for the yes_no dataset. * Refactoring: Remove unused code. * Add Colab notebook for the yesno dataset. * Add GitHub actions to run yesno. * Fix a typo. * Minor fixes. * Train more epochs for GitHub actions. * Minor fixes. * Minor fixes. * Fix style issues.
398 B
398 B
Yesno recipe
You can run the recipe with CPU.
The above Colab notebook finishes the training using CPU within two minutes (50 epochs in total).
The WER is
[test_set] %WER 0.42% [1 / 240, 0 ins, 1 del, 0 sub ]