Amazon Transcribe - Speaker Diarization Benchmark

Prerequisites

• Ubuntu 20.04 (x86_64)
• Git
• Python 3.7+
• PIP
• AWS Account

Usage

1. Clone the repository:

git clone https://github.com/Picovoice/speaker-diarization-benchmark.git

2. Install the dependencies:

pip3 install -r requirements.txt

3. Set up the dataset as described in the main readme of the repository.

4. Create an S3 bucket on you AWS account.

5. Run the benchmark:

python3 benchmark.py \
    --type {ACCURACY|CPU|MEMORY} \
    --dataset ${DATASET} \
    --data-folder ${DATA_FOLDER} \
    --label-folder ${LABEL_FOLDER} \
    --engine AWS_TRANSCRIBE \
    --aws-profile ${AWS_PROFILE} \
    --aws-s3-bucket-name ${AWS_S3_BUCKET_NAME}

Where:

• type is the type of benchmark to run. It can be ACCURACY, CPU, or MEMORY.
• dataset is the name of the dataset to use.
• data-folder is the path to the folder containing the audio files.
• label-folder is the path to the folder containing the ground truth labels.
• engine is the name of the engine to benchmark. It must be AWS_TRANSCRIBE.
• aws-profile is the name of the AWS profile to use.
• aws-s3-bucket-name is the name of the S3 bucket to use.