thewhisper-large-v3-turbo

pip install thestage
thestage config set --access-token <YOUR_ACCESS_TOKEN>

pip install 'thestage-elastic-models[nvidia]' \
    --extra-index-url https://thestage.jfrog.io/artifactory/api/pypi/pypi-thestage-ai-production/simple
pip install datasets==3.6.0 librosa soundfile  # only needed to load audio for the example below

# Install ffmpeg (required for audio processing)
# Ubuntu/Debian: apt install ffmpeg
# macOS: brew install ffmpeg
git clone https://github.com/TheStageAI/TheWhisper.git
cd TheWhisper
pip install .[nvidia]   # or pip install .[apple] for Apple Silicon

pip install thestage-elastic-models[nvidia] --extra-index-url https://thestage.jfrog.io/artifactory/api/pypi/pypi-thestage-ai-production/simple

from thestage_speechkit.nvidia import ASRPipeline

model = ASRPipeline(
    model='TheStageAI/thewhisper-large-v3-turbo',
    model_size='S',
    chunk_length_s=15,
    batch_size=32,
    device='cuda'
)

result = model(
    "path_to_your_audio.wav",
    chunk_length_s=15,
    generate_kwargs={'do_sample': False, 'num_beams': 1, 'use_cache': True}
)

print(result["text"])