---
title: "WhisperFusion"
emoji: "🌖"
colorFrom: "pink"
colorTo: "green"
sdk: "docker"
python_version: "3.10"
sdk_version: "latest"
suggested_hardware: "t4-small"
suggested_storage: "medium"
app_file: "examples/chatbot/html/main.py"
app_port: 7860
base_path: "/"
fullWidth: false
models: ["teknium/OpenHermes-2.5-Mistral-7B"]
datasets: []
tags: ["AI", "chatbot", "speech-to-text", "real-time", "TensorRT", "LLM"]
pinned: false
hf_oauth: false
hf_oauth_scopes: []
disable_embedding: false
startup_duration_timeout: "30m"
custom_headers:
  cross-origin-embedder-policy: "require-corp"
  cross-origin-opener-policy: "same-origin"
  cross-origin-resource-policy: "cross-origin"
preload_from_hub:
  - "NVIDIA/TensorRT-LLM examples/whisper/whisper_small_en,examples/phi/phi_engine,examples/phi/phi-2"
description: "WhisperFusion is an AI chatbot that provides ultra-low latency conversations. It integrates Mistral, a Large Language Model (LLM), on top of the real-time speech-to-text pipeline. It utilizes OpenAI WhisperLive to convert spoken language into text in real-time and is optimized to run as TensorRT engines, ensuring high-performance and low-latency processing."
installation: "Install [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM/blob/main/docs/source/installation.md) to build Whisper and Mistral TensorRT engines. Refer to the README and the [Dockerfile.multi](https://github.com/NVIDIA/TensorRT-LLM/blob/main/docker/Dockerfile.multi) to install the required packages in the base pytorch docker image."
usage: "Run the main.py script with the appropriate arguments to start the chatbot."
source: "This information is provided by Hugging Face."
---