jetson-examples 0.1.5__py3-none-any.whl → 0.1.7__py3-none-any.whl

reComputer/scripts/depth-anything-v2/README.md

@@ -0,0 +1,135 @@
+# Jetson-Example: Run Depth Anything V2 on NVIDIA Jetson Orin 🚀
+This project provides an one-click deployment of the Depth Anything V2 monocular depth estimation model developed by Hong Kong University and ByteDance.  The deployment is visualized on [reComputer J4012](https://www.seeedstudio.com/reComputer-J4012-p-5586.html) (Jetson Orin NX 16GB, 100 TOPS) and includes a WebUI for model conversion to TensorRT and real-time depth estimation.
+<p align="center">
+  <img src="images/WebUI.png" alt="WebUI">
+</p>
+
+All models and inference engine implemented in this project are from the official [Depth Anything V2](https://github.com/DepthAnything/Depth-Anything-V2).
+
+## 🔥Features
+
+- One-click deployment for Depth Anything V2 models.
+- WebUI for model conversion and depth estimation.
+- Support for uploading videos/images or using the local camera 
+- Supports S, B, L models of Depth Anything V2 with input sizes 518.
+
+    ### 🗝️WebUI Features
+    - **Choose model**: Select from Depth Anything V2 models. (S, B, L)
+    - **Grayscale option**: Option to use grayscale. 
+    - **Choose source**: Select the input source (Video, Image, Camera).
+    - **Export Model**: Automatically download and convert the model from ONNX to TensorRT format.
+    - **Start Estimation**: Begin depth estimation using the selected model and input source.
+    - **Stop Estimation**: Stop the ongoing depth estimation process.
+    <p align="center">
+      <img src="images/Opr.png" alt="Depthanything" width="320" height="360">
+    </p>
+
+## 🥳Getting Started
+### 📜Prerequisites
+- reComputer J4012 [(🛒Buy Here)](https://www.seeedstudio.com/reComputer-J4012-p-5586.html)
+- Docker installed on reComputer
+- USB Camera (optional)
+
+
+### Modify Docker Daemon Configuration (Optional)
+To enhance the experience of quickly loading models in Docker, you need to add the following content to the `/etc/docker/daemon.json` file:
+
+```json
+{
+  "default-runtime": "nvidia",
+  "runtimes": {
+    "nvidia": {
+      "path": "nvidia-container-runtime",
+      "runtimeArgs": []
+    }
+  },
+  "storage-driver": "overlay2",
+  "data-root": "/var/lib/docker",
+  "log-driver": "json-file",
+  "log-opts": {
+    "max-size": "100m",
+    "max-file": "3"
+  },
+  "no-new-privileges": true,
+  "experimental": false
+}
+```
+
+After modifying the `daemon.json` file, you need to restart the Docker service to apply the configuration:
+
+```sh
+sudo systemctl restart docker
+```
+
+
+### 🚀Installation
+
+
+PyPI(recommend)
+  ```sh
+  pip install jetson-examples
+  ```
+Linux (github trick)
+```sh
+curl -fsSL https://raw.githubusercontent.com/Seeed-Projects/jetson-examples/main/install.sh | sh
+```
+Github (for Developer)
+```sh
+git clone https://github.com/Seeed-Projects/jetson-examples
+cd jetson-examples
+pip install .
+```
+
+### 📋Usage
+1. Run code:
+    ```sh
+    reComputer run depth-anything-v2
+    ```
+
+2. Open a web browser and input **http://{reComputer ip}:5000**. Use the WebUI to select the model and source.
+
+3. Click on **Export Model** to download and convert the model.
+
+4. Click on **Start Estimation** to begin the depth estimation process.
+
+5. View the real-time depth estimation results on the WebUI.
+
+## ⛏️Applications
+
+- **Security**: Enhance surveillance systems with depth perception.
+  <p align="center">
+    <img src="images/Security.png" alt="Security" width="500" height="150">
+  </p>
+- **Autonomous Driving**: Improve environmental sensing for autonomous vehicles.
+  <p align="center">
+    <img src="images/Autonomous Driving.png" alt="Autonomous Driving" width="500" height="150">
+  </p>
+- **Underwater Scenes**: Apply depth estimation in underwater exploration.
+  <p align="center">
+      <img src="images/Underwater Scenes.png" alt="Underwater Scenes" width="500" height="150">
+    </p>
+- **Indoor Scenes**: Use depth estimation for indoor navigation and analysis.
+  <p align="center">
+      <img src="images/Indoor Scenes.png" alt="Indoor Scenes" width="500" height="150">
+    </p>
+
+## Further Development 🔧
+- [Depth Anything V2 Official](https://github.com/DepthAnything/Depth-Anything-V2)
+- [Depth Anything V2 TensorRT](https://github.com/spacewalk01/depth-anything-tensorrt)
+- [Depth Anything ONNX](https://github.com/fabio-sim/Depth-Anything-ONNX)
+- [Depth Anything ROS](https://github.com/scepter914/DepthAnything-ROS)
+- [Depth Anything Android](https://github.com/FeiGeChuanShu/ncnn-android-depth_anything)
+
+
+## 🙏🏻Contributing
+
+We welcome contributions from the community. Please fork the repository and create a pull request with your changes.
+
+## ✅License
+
+This project is licensed under the MIT License.
+
+## 🏷️Acknowledgements
+
+- Depth Anything V2 Official [project](https://github.com/DepthAnything/Depth-Anything-V2) by Hong Kong University and ByteDance.
+- Seeed Studio team for their [support and resources](https://github.com/Seeed-Projects/jetson-examples).

reComputer/scripts/depth-anything-v2/clean.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+CONTAINER_NAME="depth-anything-v2"
+IMAGE_NAME="yaohui1998/depthanything-v2-on-jetson-orin:latest"
+
+sudo docker stop $CONTAINER_NAME
+sudo docker rm $CONTAINER_NAME
+sudo docker rmi $IMAGE_NAMEs

reComputer/scripts/depth-anything-v2/config.yaml

@@ -0,0 +1,31 @@
+allowed_l4t_versions:
+  - 35.3.1
+  - 35.4.1
+  - 35.5.0
+required_disk_space: 15  # in GB
+min_mem_gb: 4
+min_swap_gb: 4
+nvidia_jetson_package: "nvidia-jetpack"
+packages:
+  #- "ros-noetic-ros-base"
+  #- "flask"
+docker:
+  desired_daemon_json: |
+    {
+      "default-runtime": "nvidia",
+      "runtimes": {
+        "nvidia": {
+          "path": "nvidia-container-runtime",
+          "runtimeArgs": []
+        }
+      },
+      "storage-driver": "overlay2",
+      "data-root": "/var/lib/docker",
+      "log-driver": "json-file",
+      "log-opts": {
+        "max-size": "100m",
+        "max-file": "3"
+      },
+      "no-new-privileges": true,
+      "experimental": false
+    }

reComputer/scripts/depth-anything-v2/init.sh

@@ -0,0 +1,164 @@
+#!/bin/bash
+#set color value
+RED=$(tput setaf 1)
+GREEN=$(tput setaf 2)
+YELLOW=$(tput setaf 3)
+BLUE=$(tput setaf 4)
+MAGENTA=$(tput setaf 5)
+CYAN=$(tput setaf 6)
+RESET=$(tput sgr0)
+
+echo "${CYAN}This script will install the necessary packages and configurations for running depth-anything on a Jetson Nano.${RESET}"
+
+# Install yq for parsing YAML files
+sudo apt-get update
+sudo apt-get install -y jq
+
+# Read configuration
+CURRENT_DIR="depth-anything-v2"
+CONFIG_FILE="./jetson-examples/reComputer/scripts/${CURRENT_DIR}/config.yaml"
+ALLOWED_L4T_VERSIONS=$(yq -r '.allowed_l4t_versions[]' $CONFIG_FILE)
+ALLOWED_L4T_VERSIONS_ARRAY=($ALLOWED_L4T_VERSIONS)
+REQUIRED_DISK_SPACE=$(yq -r '.required_disk_space' $CONFIG_FILE)
+MIN_MEM_GB=$(yq -r '.min_mem_gb' $CONFIG_FILE)
+MIN_SWAP_GB=$(yq -r '.min_swap_gb' $CONFIG_FILE)
+NVIDIA_JETSON_PACKAGE=$(yq -r '.nvidia_jetson_package' $CONFIG_FILE)
+PACKAGES=$(yq -r '.packages[]' $CONFIG_FILE)
+DESIRED_DAEMON_JSON=$(yq -r '.docker.desired_daemon_json' $CONFIG_FILE)
+CURRENT_DISK_SPACE=$(df -BG --output=avail / | tail -1 | sed 's/[^0-9]*//g')
+MEM_GB=$(free -g | awk '/^Mem:/{print $2}')
+SWAP_GB=$(free -g | awk '/^Swap:/{print $2}')
+
+echo "${MAGENTA}Allowed L4T versions:${RESET} ${GREEN}$ALLOWED_L4T_VERSIONS ${RESET}"
+echo "${MAGENTA}Required disk space:  ${GREEN}${REQUIRED_DISK_SPACE}G ${RESET}"
+echo "${MAGENTA}Minimum memory:  ${GREEN}${MIN_MEM_GB}G ${RESET}"
+echo "${MAGENTA}Minimum swap:  ${GREEN}${MIN_SWAP_GB}G ${RESET}" 
+echo "${MAGENTA}NVIDIA Jetson package:${RESET}  ${GREEN}$NVIDIA_JETSON_PACKAGE ${RESET}"
+echo "${MAGENTA}Additional packages: ${RESET} ${GREEN}$PACKAGES ${RESET}"
+
+# Check if NVIDIA Jetson package is installed
+if ! dpkg -l | grep -qw "$NVIDIA_JETSON_PACKAGE"; then
+    echo "$NVIDIA_JETSON_PACKAGE is not installed. Installing $NVIDIA_JETSON_PACKAGE..."
+    sudo apt-get install -y $NVIDIA_JETSON_PACKAGE
+else
+    echo "$NVIDIA_JETSON_PACKAGE is installed: ${GREEN}OK!${RESET}"
+fi
+
+# Install additional packages
+for PACKAGE in $PACKAGES; do
+    if ! dpkg -l | grep -qw "$PACKAGE"; then
+        echo "$PACKAGE is not installed. Installing $PACKAGE..."
+        sudo apt-get install -y $PACKAGE
+    else
+        echo "$PACKAGE is installed: ${GREEN}OK!${RESET}"
+    fi
+done
+
+# Get system architecture
+ARCH=$(uname -i)
+if [ "$ARCH" = "aarch64" ]; then
+    # Check for L4T version string
+    L4T_VERSION_STRING=$(head -n 1 /etc/nv_tegra_release)
+
+    if [ -z "$L4T_VERSION_STRING" ]; then
+        L4T_VERSION_STRING=$(dpkg-query --showformat='${Version}' --show nvidia-l4t-core)
+    fi
+
+    L4T_RELEASE=$(echo "$L4T_VERSION_STRING" | cut -f 2 -d ' ' | grep -Po '(?<=R)[^;]+')
+    L4T_REVISION=$(echo "$L4T_VERSION_STRING" | cut -f 2 -d ',' | grep -Po '(?<=REVISION: )[^;]+')
+    L4T_VERSION="$L4T_RELEASE.$L4T_REVISION"
+
+elif [ "$ARCH" = "x86_64" ]; then
+    echo "${RED}Unsupported architecture: $ARCH${RESET}"
+    exit 1
+fi
+
+
+# Check L4T version
+if [[ " ${ALLOWED_L4T_VERSIONS_ARRAY[@]} " =~ " ${L4T_VERSION} " ]]; then
+    echo "L4T VERSION ${GREEN}${L4T_VERSION}${RESET} is in the allowed: ${GREEN}OK!${RESET}"
+else
+    echo "${RED}L4T VERSION ${GREEN}${L4T_VERSION}${RESET}${RED} is not in the allowed versions list.${RESET}"
+    exit 1
+fi
+
+# Check disk space
+if [ "$CURRENT_DISK_SPACE" -lt "$REQUIRED_DISK_SPACE" ]; then
+    echo "${RED}Insufficient disk space. Required: ${REQUIRED_DISK_SPACE}G, Available: ${CURRENT_DISK_SPACE}G. ${RESET}"
+    exit 1
+else
+    echo "Required ${GREEN}${REQUIRED_DISK_SPACE}${RESET} G disk space: ${GREEN}OK!${RESET}"
+fi
+
+# Check memory and swap space
+if [ "$MEM_GB" -lt "$MIN_MEM_GB" ]; then
+    echo "${RED}Insufficient memory: $MEM_GB GB (minimum required: $MIN_MEM_GB GB).${RESET}"
+    exit 1
+else
+    echo "Required ${GREEN}$MIN_MEM_GB${RESET} G memory space: ${GREEN}OK!${RESET}"
+fi
+
+if [ "$SWAP_GB" -lt "$MIN_SWAP_GB" ]; then
+    echo "${RED}Insufficient swap space: $SWAP_GB GB (minimum required: $MIN_SWAP_GB GB). ${RESET}"
+    exit 1
+else
+    echo "Required ${GREEN}$MIN_SWAP_GB${RESET} G swap space: ${GREEN}OK!${RESET}"
+fi
+
+# Check if Docker is installed
+if ! command -v docker &> /dev/null; then
+    echo "${BLUE}Docker is not installed. Installing Docker...${RESET}"
+
+    sudo apt-get install -y \
+        apt-transport-https \
+        ca-certificates \
+        curl \
+        software-properties-common
+
+    curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo apt-key add -
+    sudo add-apt-repository \
+        "deb [arch=arm64] https://download.docker.com/linux/ubuntu \
+        $(lsb_release -cs) \
+        stable"
+
+    sudo apt-get update
+    sudo apt-get install -y docker-ce
+    sudo systemctl enable docker
+    sudo systemctl start docker
+    sudo usermod -aG docker $USER
+    sudo systemctl restart docker
+    newgrp docker
+
+    echo "Docker has been installed and configured."
+fi
+
+# Check if the current user has permissions to use Docker
+if ! docker info &> /dev/null; then
+    echo "The current user does not have permissions to use Docker. Adding permissions..."
+    sudo usermod -aG docker $USER
+    sudo systemctl restart docker
+    newgrp docker
+    echo "${BLUE}Permissions added. Please log out and log back in for the changes to take effect.${RESET}"
+else
+    echo "${GREEN}Docker is installed and the current user has permissions to use it.${RESET}"
+fi
+
+DAEMON_JSON_PATH="/etc/docker/daemon.json"
+if [ ! -f "$DAEMON_JSON_PATH" ] || [ "$(cat $DAEMON_JSON_PATH)" != "$DESIRED_DAEMON_JSON" ]; then
+    echo "${BLUE}Creating/updating $DAEMON_JSON_PATH with the desired content...${RESET}"
+    echo "$DESIRED_DAEMON_JSON" | sudo tee $DAEMON_JSON_PATH > /dev/null
+    sudo systemctl restart docker
+    echo "${GREEN}$DAEMON_JSON_PATH has been created/updated.${RESET}"
+else
+    echo "${GREEN}$DAEMON_JSON_PATH already exists and has the correct content.${RESET}"
+fi
+
+# Install additional packages
+for PACKAGE in $PACKAGES; do
+    if ! dpkg -l | grep -qw "$PACKAGE"; then
+        echo "${CYAN}$PACKAGE${RESET} ${BLUE}is not installed. Installing $PACKAGE...${RESET}"
+        sudo apt-get install -y $PACKAGE
+    else
+        echo "${GREEN}$PACKAGE${RESET} is already installed: ${GREEN}OK!${RESET}"
+    fi
+done

reComputer/scripts/depth-anything-v2/run.sh

@@ -0,0 +1,22 @@
+CONTAINER_NAME="depth-anything-v2"
+IMAGE_NAME="yaohui1998/depthanything-v2-on-jetson-orin:latest"
+
+# Pull the latest image
+docker pull $IMAGE_NAME
+
+# Check if the container with the specified name already exists
+if [ $(docker ps -a -q -f name=^/${CONTAINER_NAME}$) ]; then
+    echo "Container $CONTAINER_NAME already exists. Starting and attaching..."
+    docker start $CONTAINER_NAME
+else
+    echo "Container $CONTAINER_NAME does not exist. Creating and starting..."
+    docker run -it \
+        --name $CONTAINER_NAME \
+        --privileged \
+        --network host \
+        -v /tmp/.X11-unix:/tmp/.X11-unix \
+        -v /dev/*:/dev/* \
+        -v /etc/localtime:/etc/localtime:ro \
+        --runtime nvidia \
+        $IMAGE_NAME
+fi

reComputer/scripts/llama-factory/README.md

@@ -2,6 +2,7 @@
 
 
 ## Hello
+Now you can tailor a custom private local LLM to meet your requirements.
 
 💡 Here's an example of quickly deploying [Llama-Factory](https://github.com/hiyouga/LLaMA-Factory) on Jetson device.
 
@@ -12,15 +13,15 @@
 
 🛠️ Follow the tutorial below to quickly experience the performance of Llama-Factory on edge computing devices.
 
-<!-- <div align="center">
-  <img alt="yolov10" width="1200px" src="./assets/llama-factory-Jetson.png">
-</div> -->
+<div align="center">
+  <img alt="training" width="1200px" src="./assets/training.gif">
+</div>
 
 ## Get a Jetson Orin Device 🛒
 | Device Model | Description | Link |
 |--------------|-------------|------|
 | reComputer J4012, powered by Orin NX 16GB, 100 TOPS | Embedded computer powered by Orin NX | [Buy Here](https://www.seeedstudio.com/reComputer-J4012-p-5586.html) |
-| NVIDIA® Jetson AGX Orin™ 64GB Developer Kit | smallest and most powerful AI edge computer | [Buy Here](https://www.seeedstudio.com/NVIDIArJetson-AGX-Orintm-64GB-Developer-Kit-p-5641.html) |
+| NVIDIA® Jetson AGX Orin™ 64GB Developer Kit | Smallest and most powerful AI edge computer | [Buy Here](https://www.seeedstudio.com/NVIDIArJetson-AGX-Orintm-64GB-Developer-Kit-p-5641.html) |
 
 ## Getting Started
 

reComputer/scripts/llama3/clean.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+BASE_PATH=/home/$USER/reComputer
+JETSON_REPO_PATH="$BASE_PATH/jetson-containers"
+# search local image
+img_tag=$($JETSON_REPO_PATH/autotag -p local ollama)
+# 检查返回值
+if [ $? -eq 0 ]; then
+    echo "Found Image successfully."
+    sudo docker rmi $img_tag
+else
+    echo "[warn] Found Image failed with error code $?. skip delete Image."
+fi
+# 
+# 4 build whl
+read -p "Delete all data for ollama? (y/n): " choice
+if [[ $choice == "y" || $choice == "Y" ]]; then
+    echo "Delete=> $JETSON_REPO_PATH/data/models/ollama/"
+    sudo rm -rf $JETSON_REPO_PATH/data/models/ollama/
+    echo "Clean Data Done."
+else
+    echo "[warn] Skip Clean Data."
+fi

reComputer/scripts/ollama/clean.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+BASE_PATH=/home/$USER/reComputer
+JETSON_REPO_PATH="$BASE_PATH/jetson-containers"
+# search local image
+img_tag=$($JETSON_REPO_PATH/autotag -p local ollama)
+# 检查返回值
+if [ $? -eq 0 ]; then
+    echo "Found Image successfully."
+    sudo docker rmi $img_tag
+else
+    echo "[warn] Found Image failed with error code $?. skip delete Image."
+fi
+# 
+# 4 build whl
+read -p "Delete all data for ollama? (y/n): " choice
+if [[ $choice == "y" || $choice == "Y" ]]; then
+    echo "Delete=> $JETSON_REPO_PATH/data/models/ollama/"
+    sudo rm -rf $JETSON_REPO_PATH/data/models/ollama/
+    echo "Clean Data Done."
+else
+    echo "[warn] Skip Clean Data."
+fi

reComputer/scripts/parler-tts/clean.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+# get image
+source ./getVersion.sh
+
+# remove docker image
+sudo docker rmi feiticeir0/parler-tts:${TAG_IMAGE}

reComputer/scripts/parler-tts/getVersion.sh

@@ -0,0 +1,59 @@
+#!/bin/bash
+# based on dusty - https://github.com/dusty-nv/jetson-containers/blob/master/jetson_containers/l4t_version.sh
+# and llama-factory init script
+
+# we only have images for these - 36.2.0 works on 36.3.0
+L4T_VERSIONS=("35.3.1", "35.4.1", "36.2.0", "36.3.0")
+
+ARCH=$(uname -i)
+# echo "ARCH:  $ARCH"
+
+if [ $ARCH = "aarch64" ]; then
+	L4T_VERSION_STRING=$(head -n 1 /etc/nv_tegra_release)
+
+	if [ -z "$L4T_VERSION_STRING" ]; then
+		#echo "reading L4T version from \"dpkg-query --show nvidia-l4t-core\""
+
+		L4T_VERSION_STRING=$(dpkg-query --showformat='${Version}' --show nvidia-l4t-core)
+		L4T_VERSION_ARRAY=(${L4T_VERSION_STRING//./ })
+
+		#echo ${L4T_VERSION_ARRAY[@]}
+		#echo ${#L4T_VERSION_ARRAY[@]}
+
+		L4T_RELEASE=${L4T_VERSION_ARRAY[0]}
+		L4T_REVISION=${L4T_VERSION_ARRAY[1]}
+	else
+		#echo "reading L4T version from /etc/nv_tegra_release"
+
+		L4T_RELEASE=$(echo $L4T_VERSION_STRING | cut -f 2 -d ' ' | grep -Po '(?<=R)[^;]+')
+		L4T_REVISION=$(echo $L4T_VERSION_STRING | cut -f 2 -d ',' | grep -Po '(?<=REVISION: )[^;]+')
+	fi
+
+	L4T_REVISION_MAJOR=${L4T_REVISION:0:1}
+	L4T_REVISION_MINOR=${L4T_REVISION:2:1}
+
+	L4T_VERSION="$L4T_RELEASE.$L4T_REVISION"
+
+	IMAGE_TAG=$L4T_VERSION
+
+	#echo "L4T_VERSION :  $L4T_VERSION"
+	#echo "L4T_RELEASE :  $L4T_RELEASE"
+	#echo "L4T_REVISION:  $L4T_REVISION"
+
+elif [ $ARCH != "x86_64" ]; then
+	echo "unsupported architecture:  $ARCH"
+	exit 1
+fi
+
+
+if [[ ! " ${L4T_VERSIONS[@]} " =~ " ${L4T_VERSION} " ]]; then
+    echo "L4T_VERSION is not in the allowed versions list. Exiting."
+    exit 1
+fi
+
+# check if 36 to change IMAGE_TAG
+if [ ${L4T_RELEASE} -eq "36" ]; then
+	# image tag will be 2.0
+	IMAGE_TAG="36.2.0"
+fi
+

reComputer/scripts/parler-tts/init.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+echo "Creating models directory at /home/$USER/models"
+
+# Create Model dir in User home
+mkdir /home/$USER/models
+
+

reComputer/scripts/parler-tts/readme.md

@@ -0,0 +1,63 @@
+# Parler TTS Mini: Expresso
+
+
+Parler-TTS Mini: Expresso is a fine-tuned version of Parler-TTS Mini v0.1 on the Expresso dataset. It is a lightweight text-to-speech (TTS) model that can generate high-quality, natural sounding speech. Compared to the original model, Parler-TTS Expresso provides superior control over emotions (happy, confused, laughing, sad) and consistent voices (Jerry, Thomas, Elisabeth, Talia).
+
+[You can get more information on HuggingFace](https://huggingface.co/parler-tts/parler-tts-mini-expresso)
+
+![Gradio Interface] (audio1.png)
+![Gradio Interface result] (audio2.png)
+
+## Getting started
+#### Prerequisites
+* SeeedStudio reComputer J402 [Buy one](https://www.seeedstudio.com/reComputer-J4012-p-5586.html)
+* Audio Columns
+* Docker installed
+
+## Instalation
+PyPI (best)
+
+```bash
+pip install jetson-examples
+```
+
+## Usage
+### Method 1
+##### If you're running inside your reComputer
+1. Type the following command in a terminal
+```bash
+reComputer run parler-tts
+```
+2. Open a web browser and go to [http://localhost:7860](http://localhost:7860)
+3. A Gradio interface will appear with two text boxes
+    1. The first for you to write the text that will be converted to audio
+    2. A second one for you to describe the speaker: Male/Female, tone, pitch, mood, etc.. See the examples in Parler-tts page. 
+4. When you press submit, after a while, the audio will appear on the right box. You can also download the file if yo want. 
+
+### Method 2
+##### If you want to connect remotely with ssh to the reComputer
+1. Connect using SSH but redirecting the 7860 port
+```bash
+ssh -L 7860:localhost:7860 <username>@<reComputer_IP>
+```
+2. Type the following command in a terminal
+```bash
+reComputer run parler-tts
+```
+3. Open a web browser (on your machine) and go to [http://localhost:7860](http://localhost:7860)
+
+4. The same instructions above. 
+
+## Manual Run
+
+If you want to run the docker image outside jetson-examples, here's the command:
+
+```bash
+docker run --rm -p 7860:7860 --runtime=nvidia -v $(MODELS_DIR):/app feiticeir0/parler_tts:r36.2.0
+```
+
+**MODELS_DIR** is a directory where HuggingFace will place the models downloaded from its hub.  If you want to run the image several times, the code will only download the model once, if that diretory stays the same. 
+
+This is controlled by an environment variable called HF_HOME. 
+
+[More info about HF environment variables](https://huggingface.co/docs/huggingface_hub/package_reference/environment_variables)

reComputer/scripts/parler-tts/run.sh

@@ -0,0 +1,17 @@
+#!/bin/bash
+
+MODELS_DIR=/home/$USER/models
+
+# get L4T version
+# it exports a variable IMAGE_TAG
+source ./getVersion.sh
+
+# pull docker image
+echo "docker push feiticeir0/parler_tts:${IMAGE_TAG}"
+
+docker run \
+	--rm \
+	-p 7860:7860 \
+	--runtime=nvidia \
+	-v $(MODELS_DIR):/app \
+	feiticeir0/parler_tts:${IMAGE_TAG}

reComputer/scripts/run.sh

@@ -1,4 +1,9 @@
 #!/bin/bash
+handle_error() {
+    echo "An error occurred. Exiting..."
+    exit 1
+}
+trap 'handle_error' ERR
 
 check_is_jetson_or_not() {
     model_file="/proc/device-tree/model"