Whisper Speech-to-Text Benchmark

Prerequisites

• Ubuntu 20.04 (x86_64)
• Git
• Python
• PIP

Usage

1. Clone the repository:

git clone https://github.com/Picovoice/speech-to-text-benchmark.git

2. Install the dependencies:

pip3 install -r requirements.txt

4. Run the benchmark:

python3 benchmark.py \
--engine ${WHISPER_MODEL} \
--dataset ${DATASET} \
--dataset-folder ${DATASET_FOLDER} \
--language ${LANGUAGE} \