Azure - Speaker Diarization Benchmark
- Ubuntu 20.04 (x86_64)
- Python 3.7+
- Azure Account
- Clone the repository:
- Install the dependencies:
Set up the dataset as described in the main readme of the repository.
A client library for the Speech to Text REST API should be generated, as outlined in the documentation.
Create an Azure Storage account on you Azure account.
Run the benchmark:
typeis the type of benchmark to run. It can be
datasetis the name of the dataset to use.
data-folderis the path to the folder containing the audio files.
label-folderis the path to the folder containing the ground truth labels.
engineis the name of the engine to benchmark. It must be
azure-storage-account-nameis the name of the Azure Storage account to use.
azure-storage-account-keyis the key of the Azure Storage account to use.
azure-storage-container-nameis the name of the Azure Storage container to use.
azure-subscription-keyis the subscription key to use.
azure-regionis the region to use.