speechtotext.benchmark.benchmarks.run_benchmarks

run_benchmarks(benchmark_class_list, benchmark_dataset, number_of_samples, report_name)

Run al benchmarks out of list.

Parameters:

• benchmark_list (list[Benchmark]) – List of benchmark classes to run.

• dataset (Dataset) – Dataset to use for benchmark.

• number_of_samples (int) – Number of samples used in benchmark.

• report_name (str) – Name of report. To save the errors to.

Return type:

list[DataFrame]