Added
- Support for evaluation of local Hugging Face models.
- Tests for the `question_answering`-task.
- The `automatic_speech_recognition`-task.
- Util functions, `leaderboard_utils`, for interacting with the associated REST-api which interacts with the leaderboard holding the evaluation results.
- A new function in the `evaluator` module, called `_send_results_to_leaderboard` which sends evaluation results to the leaderboard using the util functions from `leaderboard_utils`, and tests for this function and `leaderboard_utils`.
- The `discourse-coherence`-task.
- Support for integer labels.