feat: add dockerfile

README.md

@@ -1,11 +1,31 @@
-
-title: WhisperFusion
-emoji: 🌖
-colorFrom: pink
-colorTo: green
-sdk: docker
+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
-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.
+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."