Google STT - Speaker Diarization Benchmark

Prerequisites

• Ubuntu 20.04 (x86_64)
• Git
• Python 3.7+
• PIP
• Google Cloud 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 a Google Cloud storage bucket on you Google Cloud account.

5. Run the benchmark:

python3 benchmark.py \
    --type {ACCURACY|CPU|MEMORY} \
    --dataset ${DATASET} \
    --data-folder ${DATA_FOLDER} \
    --label-folder ${LABEL_FOLDER} \
    --engine {GOOGLE_SPEECH_TO_TEXT|GOOGLE_SPEECH_TO_TEXT_ENHANCED} \
    --gcp-credentials ${GCP_CREDENTIALS} \
    --gcp-bucket-name ${GCP_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 label files.
• gcp-credentials is the path to the Google Cloud credentials file.
• gcp-bucket-name is the name of the Google Cloud storage bucket.
• gcp-region is the region of the Google Cloud storage bucket.
• engine is the name of the engine to benchmark. It can be GOOGLE_SPEECH_TO_TEXT or GOOGLE_SPEECH_TO_TEXT_ENHANCED depending on the type of benchmark to run.