Welcome to WhisperFusion. WhisperFusion builds upon the capabilities of the WhisperLive and WhisperSpeech by integrating Mistral, a Large Language Model (LLM), on top of the real-time speech-to-text pipeline. Both LLM and Whisper are optimized to run efficiently as TensorRT engines, maximizing performance and real-time processing capabilities. While WhiperSpeech is optimized with torch.compile.
Real-Time Speech-to-Text: Utilizes OpenAI WhisperLive to convert spoken language into text in real-time.
Large Language Model Integration: Adds Mistral, a Large Language Model, to enhance the understanding and context of the transcribed text.
TensorRT Optimization: Both LLM and Whisper are optimized to run as TensorRT engines, ensuring high-performance and low-latency processing.
torch.compile: WhisperSpeech uses torch.compile to speed up inference which makes PyTorch code run faster by JIT-compiling PyTorch code into optimized kernels.
The demo was run on a single RTX 4090 GPU. WhisperFusion uses the Nvidia TensorRT-LLM library for CUDA optimized versions of popular LLM models. TensorRT-LLM supports multiple GPUs, so it should be possible to run WhisperFusion for even better performance on multiple GPUs.
We provide a Docker Compose setup to streamline the deployment of the pre-built TensorRT-LLM docker container. This setup includes both Whisper and Phi converted to TensorRT engines, and the WhisperSpeech model is pre-downloaded to quickly start interacting with WhisperFusion. Additionally, we include a simple web server for the Web GUI.
mkdir docker/scratch-space
cp docker/scripts/build-* docker/scripts/run-whisperfusion.sh docker/scratch-space/
docker compose build export MODEL=Phi-3-mini-4k-instruct #Phi-3-mini-128k-instruct or phi-2, By default WhisperFusion uses phi-2 docker compose up
- Start Web GUI on `http://localhost:8000`
**NOTE**
## Contact Us
For questions or issues, please open an issue. Contact us at:
marcus.edel@collabora.com, jpc@collabora.com,
vineet.suryan@collabora.com