halo ini project fruitszone

app.ipynb

@@ -0,0 +1,240 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Buah Alpukat',\n",
+       " 'Buah Apel',\n",
+       " 'Buah Belimbing',\n",
+       " 'Buah Naga',\n",
+       " 'Buah Lemon',\n",
+       " 'Buah Nanas',\n",
+       " 'Buah Pir',\n",
+       " 'Buah Pisang',\n",
+       " 'Buah Salak',\n",
+       " 'Buah Stroberi']"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from fastai.vision.all import *\n",
+    "\n",
+    "learn = load_learner('model.pkl')\n",
+    "\n",
+    "\n",
+    "def format_name(name):\n",
+    "    if name != 'buah naga':\n",
+    "        return f'Buah {name.title()}'\n",
+    "    \n",
+    "    return name.title()\n",
+    "\n",
+    "\n",
+    "names = list(map(format_name, learn.dls.vocab))\n",
+    "names\n",
+    "\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import firebase_admin\n",
+    "from firebase_admin import credentials\n",
+    "from firebase_admin import firestore\n",
+    "\n",
+    "cred = credentials.Certificate('firebase_key.json')\n",
+    "app = firebase_admin.initialize_app(cred)\n",
+    "db = firestore.client()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc_ref = db.collection(u'preds').add({\n",
+    "    u'image': u'Lovelace',\n",
+    "    u'prediction': 1815,\n",
+    "    u'time_added': firestore.SERVER_TIMESTAMP\n",
+    "})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "preds_ref = db.collection(u'preds')\n",
+    "docs = preds_ref.stream()\n",
+    "\n",
+    "for doc in docs:\n",
+    "    data = base64.b64decode(doc.to_dict()['image'])\n",
+    "    buff = BytesIO(data)\n",
+    "    img = Image.open(buff)\n",
+    "    img.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://127.0.0.1:7860\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"900\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "(<gradio.routes.App at 0x7f3279fb6af0>, 'http://127.0.0.1:7860/', None)"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "    /* Turns off some styling */\n",
+       "    progress {\n",
+       "        /* gets rid of default border in Firefox and Opera. */\n",
+       "        border: none;\n",
+       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
+       "        background-size: auto;\n",
+       "    }\n",
+       "    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
+       "        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
+       "    }\n",
+       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
+       "        background: #F44336;\n",
+       "    }\n",
+       "</style>\n"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import gradio as gr\n",
+    "from fastai.vision.all import *\n",
+    "import firebase_admin\n",
+    "from firebase_admin import credentials\n",
+    "from firebase_admin import firestore\n",
+    "import base64\n",
+    "from io import BytesIO\n",
+    "\n",
+    "cred = credentials.Certificate('firebase_key.json')\n",
+    "app = firebase_admin.initialize_app(cred)\n",
+    "db = firestore.client()\n",
+    "\n",
+    "learn = load_learner('model.pkl')\n",
+    "names = list(map(lambda name: name.title(), learn.dls.vocab))\n",
+    "\n",
+    "\n",
+    "def classify(image):\n",
+    "    buffered = BytesIO()\n",
+    "    image.save(buffered, format=\"JPEG\")\n",
+    "    img_str = base64.b64encode(buffered.getvalue())\n",
+    "\n",
+    "    pred, idx, probs = learn.predict(np.asarray(image))\n",
+    "\n",
+    "    db.collection(u'preds').add({\n",
+    "        u'image': img_str,\n",
+    "        u'prediction': pred.title(),\n",
+    "        u'time_added': firestore.SERVER_TIMESTAMP\n",
+    "    })\n",
+    "\n",
+    "    return dict(zip(names, map(float, probs)))\n",
+    "\n",
+    "\n",
+    "with gr.Blocks() as demo:\n",
+    "    with gr.Row():\n",
+    "        with gr.Column():\n",
+    "            image_input = gr.Image(label=\"Gambar\", shape=(200, 200), type='pil')\n",
+    "            predict_btn = gr.Button(\"Klasifikasi\", variant='primary')\n",
+    "        with gr.Column():\n",
+    "            chart = gr.Label(label=\"Hasil\")\n",
+    "\n",
+    "    predict_btn.click(fn=classify, inputs=image_input,\n",
+    "                      outputs=chart, api_name='classify_image')\n",
+    "\n",
+    "demo.launch()\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.9.12 ('base')",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.12"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "fdff80770fe959a274e11f3f42c90636d375da6f3b1d0ebe5804fc741631cbf3"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

app.py

@@ -0,0 +1,67 @@
+import base64
+from io import BytesIO
+
+import firebase_admin
+import gradio as gr
+import numpy as np
+from fastai.vision.all import *
+import json
+from firebase_admin import credentials, firestore
+import pathlib
+
+temp = pathlib.PosixPath
+pathlib.PosixPath = pathlib.WindowsPath
+
+cred = credentials.Certificate("firebase_key.json")
+app = firebase_admin.initialize_app(cred)
+db = firestore.client()
+
+learn = load_learner("model.pkl")
+names = json.load(open("./translations.json"))
+
+
+def classify(image):
+    buffered = BytesIO()
+    image.save(buffered, format="JPEG")
+    img_str = base64.b64encode(buffered.getvalue())
+
+    pred, idx, probs = learn.predict(np.asarray(image))
+
+    db.collection("preds").add(  # inilo db
+        {
+            "image": img_str,
+            "prediction": pred.title(),
+            "time_added": firestore.SERVER_TIMESTAMP,
+        }
+    )
+
+    return [
+        names[pred]["id"],
+        names[pred]["en"],
+        f"./audios/en/{pred}.mp3",
+        f"./audios/id/{pred}.mp3",
+    ]
+
+
+with gr.Blocks(
+    css=".gradio-container {background-image: url('file=Fruitzone.jpg')}"
+) as demo:
+    with gr.Row():
+        with gr.Column():
+            image_input = gr.Webcam(label="Gambar", shape=(200, 200), type="pil")
+            predict_btn = gr.Button("Cek Nama Buah Yuk", variant="primary")
+
+        with gr.Column():
+            id_fruit_name = gr.Label(label="Bahasa indonesia")
+            en_fruit_name = gr.Label(label="Bahasa inggris")
+            en_audio = gr.Audio(label="Audio inggris")
+            id_audio = gr.Audio(label="Audio indonesia")
+
+    predict_btn.click(
+        fn=classify,
+        inputs=image_input,
+        outputs=[id_fruit_name, en_fruit_name, id_audio, en_audio],
+        api_name="classify_image",
+    )
+
+demo.launch()

app_coba.py

@@ -0,0 +1,76 @@
+import base64
+from io import BytesIO
+
+import firebase_admin
+import gradio as gr
+import numpy as np
+from fastai.vision.all import *
+import json
+from firebase_admin import credentials, firestore
+import pathlib
+
+temp = pathlib.PosixPath
+pathlib.PosixPath = pathlib.WindowsPath
+
+cred = credentials.Certificate("firebase_key.json")
+app = firebase_admin.initialize_app(cred)
+db = firestore.client()
+
+learn = load_learner("model.pkl")
+names = json.load(open("./translations.json"))
+
+
+def classify(image):
+    buffered = BytesIO()
+    image.save(buffered, format="JPEG")
+    img_str = base64.b64encode(buffered.getvalue())
+
+    pred, idx, probs = learn.predict(np.asarray(image))
+
+    db.collection("preds").add(
+        {
+            "image": img_str,
+            "prediction": pred.title(),
+            "time_added": firestore.SERVER_TIMESTAMP,
+        }
+    )
+
+    return [
+        names[pred]["id"],
+        names[pred]["en"],
+        f"./audios/en/{pred}.mp3",
+        f"./audios/id/{pred}.mp3",
+    ]
+
+
+with gr.Blocks(
+    css=".gradio-container {background-image: url('file=Background\fix.png');background-size: cover; background-size: 100% 100%;}"
+) as demo:
+    with gr.Row():
+        with gr.Column():
+            image_input = gr.Webcam(label="Gambar", shape=(200, 200), type="pil")
+            predict_id_btn = gr.Button("Prediksi Bahasa Indonesia", variant="primary")
+            predict_en_btn = gr.Button("Predict English", variant="primary")
+
+        with gr.Column():
+            id_fruit_name = gr.Label(label="Bahasa Indonesia")
+            id_audio = gr.Audio(label="Audio Indonesia")
+        with gr.Column():
+            en_fruit_name = gr.Label(label="English")
+            en_audio = gr.Audio(label="English Audio")
+
+    predict_id_btn.click(
+        fn=classify,
+        inputs=image_input,
+        outputs=[id_fruit_name, id_audio],
+        api_name="classify_image",
+    )
+
+    predict_en_btn.click(
+        fn=classify,
+        inputs=image_input,
+        outputs=[en_fruit_name, en_audio],
+        api_name="classify_image",
+    )
+
+demo.launch()

jalur.py

@@ -0,0 +1,8 @@
+import os
+
+file_path = "audios/en/Srikaya.mp3"  # Ganti dengan jalur file yang ingin Anda periksa
+
+if os.path.exists(file_path):
+    print("File ada.")
+else:
+    print("File tidak ada atau jalur file salah.")

playground.ipynb

@@ -0,0 +1,209 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from fastai.vision.all import *\n",
+    "\n",
+    "learn = load_learner('model.pkl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import firebase_admin\n",
+    "from firebase_admin import credentials\n",
+    "from firebase_admin import firestore\n",
+    "import base64\n",
+    "from io import BytesIO\n",
+    "\n",
+    "cred = credentials.Certificate('firebase_key.json')\n",
+    "app = firebase_admin.initialize_app(cred)\n",
+    "db = firestore.client()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc_ref = db.collection(u'preds').add({\n",
+    "    u'image': u'Lovelace',\n",
+    "    u'prediction': 1815,\n",
+    "    u'time_added': firestore.SERVER_TIMESTAMP\n",
+    "})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "preds_ref = db.collection(u'preds')\n",
+    "docs = preds_ref.stream()\n",
+    "\n",
+    "for doc in docs:\n",
+    "    data = base64.b64decode(doc.to_dict()['image'])\n",
+    "    buff = BytesIO(data)\n",
+    "    img = Image.open(buff)\n",
+    "    img.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://127.0.0.1:7860\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"900\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "(<gradio.routes.App at 0x7f3279fb6af0>, 'http://127.0.0.1:7860/', None)"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<style>\n",
+       "    /* Turns off some styling */\n",
+       "    progress {\n",
+       "        /* gets rid of default border in Firefox and Opera. */\n",
+       "        border: none;\n",
+       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
+       "        background-size: auto;\n",
+       "    }\n",
+       "    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
+       "        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
+       "    }\n",
+       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
+       "        background: #F44336;\n",
+       "    }\n",
+       "</style>\n"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import gradio as gr\n",
+    "from fastai.vision.all import *\n",
+    "import firebase_admin\n",
+    "from firebase_admin import credentials\n",
+    "from firebase_admin import firestore\n",
+    "import base64\n",
+    "from io import BytesIO\n",
+    "\n",
+    "cred = credentials.Certificate('firebase_key.json')\n",
+    "app = firebase_admin.initialize_app(cred)\n",
+    "db = firestore.client()\n",
+    "\n",
+    "learn = load_learner('model.pkl')\n",
+    "names = list(map(lambda name: name.title(), learn.dls.vocab))\n",
+    "\n",
+    "\n",
+    "def classify(image):\n",
+    "    buffered = BytesIO()\n",
+    "    image.save(buffered, format=\"JPEG\")\n",
+    "    img_str = base64.b64encode(buffered.getvalue())\n",
+    "\n",
+    "    pred, idx, probs = learn.predict(np.asarray(image))\n",
+    "\n",
+    "    db.collection(u'preds').add({\n",
+    "        u'image': img_str,\n",
+    "        u'prediction': pred.title(),\n",
+    "        u'time_added': firestore.SERVER_TIMESTAMP\n",
+    "    })\n",
+    "\n",
+    "    return dict(zip(names, map(float, probs)))\n",
+    "\n",
+    "\n",
+    "with gr.Blocks() as demo:\n",
+    "    with gr.Row():\n",
+    "        with gr.Column():\n",
+    "            image_input = gr.Image(label=\"Gambar\", shape=(200, 200), type='pil')\n",
+    "            predict_btn = gr.Button(\"Klasifikasi\", variant='primary')\n",
+    "        with gr.Column():\n",
+    "            chart = gr.Label(label=\"Hasil\")\n",
+    "\n",
+    "    predict_btn.click(fn=classify, inputs=image_input,\n",
+    "                      outputs=chart, api_name='classify_image')\n",
+    "\n",
+    "demo.launch()\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.9.13 64-bit",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13 (tags/v3.9.13:6de2ca5, May 17 2022, 16:36:42) [MSC v.1929 64 bit (AMD64)]"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "b671c20432fcd147198c92e7f072af9e705f087eb990bee22b07f08caab9f630"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

requirements.txt

@@ -0,0 +1,2 @@
+fastai
+firebase_admin

test.py

@@ -0,0 +1,103 @@
+import base64
+from io import BytesIO
+
+import firebase_admin
+import gradio as gr
+import numpy as np
+from fastai.vision.all import *
+import json
+from firebase_admin import credentials, firestore
+import pathlib
+
+temp = pathlib.PosixPath
+pathlib.PosixPath = pathlib.WindowsPath
+
+cred = credentials.Certificate("firebase_key.json")
+app = firebase_admin.initialize_app(cred)
+db = firestore.client()
+
+learn = load_learner("model.pkl")
+names = json.load(open("./translations.json"))
+
+with gr.Blocks(
+    css=".gradio-container {background-image: url('file=Background/4.jpeg');background-size: cover; background-size: 100% 100%;}"  # .block.svelte-kz0ejz{background-color: rgba(0,0,0,0);} kalo butuh transparan
+) as demo:
+    gr.Markdown(" ")
+    gr.Markdown(" ")
+    with gr.Row():
+        with gr.Column():
+            image_input = gr.Webcam(label="Gambar", shape=(200, 200), type="pil")
+            with gr.Row():
+                predict_id_btn = gr.Button("Bahasa Indonesia", variant="primary")
+                predict_en_btn = gr.Button("Bahasa Inggris", variant="secondary")
+
+        with gr.Column():
+            with gr.Column(visible=False) as id_fruit_name_col:
+                id_fruit_name = gr.Label(label="Bahasa indonesia")
+                id_audio = gr.Audio(label="Audio indonesia")
+            with gr.Column(visible=False) as en_fruit_name_col:
+                en_fruit_name = gr.Label(label="Bahasa inggris")
+                en_audio = gr.Audio(label="Audio inggris")
+
+    def classify_id(image):
+        buffered = BytesIO()
+        image.save(buffered, format="JPEG")
+        img_str = base64.b64encode(buffered.getvalue())
+
+        pred, idx, probs = learn.predict(np.asarray(image))
+
+        db.collection("preds").add(  # inilo db
+            {
+                "image": img_str,
+                "prediction": pred.title(),
+                "time_added": firestore.SERVER_TIMESTAMP,
+            }
+        )
+        id_fruit_name_col = gr.update(visible=True)
+        en_fruit_name_col = gr.update(visible=False)
+        return [
+            names[pred]["id"],
+            f"./audios/id/" + names[pred]["id"] + ".mp3",
+            id_fruit_name_col,
+            en_fruit_name_col,
+        ]
+
+    def classify_en(image):
+        buffered = BytesIO()
+        image.save(buffered, format="JPEG")
+        img_str = base64.b64encode(buffered.getvalue())
+
+        pred, idx, probs = learn.predict(np.asarray(image))
+
+        db.collection("preds").add(  # inilo db
+            {
+                "image": img_str,
+                "prediction": pred.title(),
+                "time_added": firestore.SERVER_TIMESTAMP,
+            }
+        )
+        en_fruit_name_col = gr.update(visible=True)
+        id_fruit_name_col = gr.update(visible=False)
+        return [
+            names[pred]["en"],
+            f"./audios/en/" + names[pred]["id"] + ".mp3",
+            id_fruit_name_col,
+            en_fruit_name_col,
+        ]
+
+    predict_id_btn.click(
+        fn=classify_id,
+        inputs=image_input,
+        outputs=[id_fruit_name, id_audio, id_fruit_name_col, en_fruit_name_col],
+        api_name="classify_image",
+    )
+    predict_en_btn.click(
+        fn=classify_en,
+        inputs=image_input,
+        outputs=[en_fruit_name, en_audio, id_fruit_name_col, en_fruit_name_col],
+        api_name="classify_image",
+    )
+
+
+# demo.launch(share=True)
+demo.launch()

test2.py

@@ -0,0 +1,95 @@
+import base64
+from io import BytesIO
+
+import firebase_admin
+import gradio as gr
+import numpy as np
+from fastai.vision.all import *
+import json
+from firebase_admin import credentials, firestore
+import pathlib
+
+temp = pathlib.PosixPath
+pathlib.PosixPath = pathlib.WindowsPath
+
+cred = credentials.Certificate("firebase_key.json")
+app = firebase_admin.initialize_app(cred)
+db = firestore.client()
+
+learn = load_learner("model.pkl")
+names = json.load(open("./translations.json"))
+
+
+def classify_id(image):
+    buffered = BytesIO()
+    image.save(buffered, format="JPEG")
+    img_str = base64.b64encode(buffered.getvalue())
+
+    pred, idx, probs = learn.predict(np.asarray(image))
+
+    db.collection("preds").add(  # inilo db
+        {
+            "image": img_str,
+            "prediction": pred.title(),
+            "time_added": firestore.SERVER_TIMESTAMP,
+        }
+    )
+
+    return [
+        names[pred]["id"],
+        f"./audios/id/" + names[pred]["id"] + ".mp3",
+    ]
+
+
+def classify_en(image):
+    buffered = BytesIO()
+    image.save(buffered, format="JPEG")
+    img_str = base64.b64encode(buffered.getvalue())
+
+    pred, idx, probs = learn.predict(np.asarray(image))
+
+    db.collection("preds").add(  # inilo db
+        {
+            "image": img_str,
+            "prediction": pred.title(),
+            "time_added": firestore.SERVER_TIMESTAMP,
+        }
+    )
+
+    return [
+        # names[pred]["id"],
+        names[pred]["en"],
+        f"./audios/en/" + names[pred]["id"] + ".mp3",
+    ]
+
+
+with gr.Blocks(
+    css=".gradio-container {background-image: url('file=Background/Fruitzone.jpg');background-size: cover; background-size: 100% 100%;}.block.svelte-kz0ejz{background-color: rgba(0,0,0,0);}"
+) as demo:
+    with gr.Row():
+        with gr.Column():
+            image_input = gr.Webcam(label="Gambar", shape=(200, 200), type="pil")
+            predict_id_btn = gr.Button("Bahasa Indonesia", variant="primary")
+            predict_en_btn = gr.Button("Bahasa Inggris", variant="secondary")
+
+        with gr.Column():
+            id_fruit_name = gr.Label(label="Bahasa indonesia", visible=False)
+            id_audio = gr.Audio(label="Audio indonesia", visible=False)
+            en_fruit_name = gr.Label(label="Bahasa inggris", visible=False)
+            en_audio = gr.Audio(label="Audio inggris", visible=False)
+
+    predict_id_btn.click(
+        fn=classify_id,
+        inputs=image_input,
+        outputs=[id_fruit_name, id_audio],
+        api_name="classify_image",
+    )
+    predict_en_btn.click(
+        fn=classify_en,
+        inputs=image_input,
+        outputs=[en_fruit_name, en_audio],
+        api_name="classify_image",
+    )
+
+
+demo.launch()

translations.json

@@ -0,0 +1,86 @@
+{
+  "apel": {
+    "id": "Apel",
+    "en": "Apple"
+  },
+  "anggur": {
+    "id": "anggur",
+    "en": "grape"
+  },
+  "alpukat": {
+    "id": "Alpukat",
+    "en": "Avocado"
+  },
+  "belimbing": {
+    "id": "Belimbing",
+    "en": "Starfruit"
+  },
+  "buah naga": {
+    "id": "Buah Naga",
+    "en": "Dragonfruit"
+  },
+  "delima": {
+    "id": "Delima",
+    "en": "Pomegranate"
+  },
+  "durian": {
+    "id": "Durian",
+    "en": "Durian"
+  },
+  "jeruk": {
+    "id": "Jeruk",
+    "en": "Orange"
+  },
+  "kiwi": {
+    "id": "Kiwi",
+    "en": "Kiwi"
+  },
+  "lemon": {
+    "id": "Lemon",
+    "en": "Lemon"
+  },
+  "mangga": {
+    "id": "Mangga",
+    "en": "Mango"
+  },
+  "manggis": {
+    "id": "Manggis",
+    "en": "mangosteen"
+  },
+  "melon": {
+    "id": "Melon",
+    "en": "Melon"
+  },
+  "nanas": {
+    "id": "Nanas",
+    "en": "Pineapple"
+  },
+  "pir": {
+    "id": "Pir",
+    "en": "Pear"
+  },
+  "pisang": {
+    "id": "Pisang",
+    "en": "Banana"
+  },
+  "rambutan": {
+    "id": "Rambutan",
+    "en": "Rambutan"
+  },
+  "salak": {
+    "id": "Salak",
+    "en": "Snakefruit"
+  },
+  "semangka": {
+    "id": "Semangka",
+    "en": "Watermelon"
+  },
+  "srikaya": {
+    "id": "Srikaya",
+    "en": "Srikaya"
+  },
+  "stroberi": {
+    "id": "Stroberi",
+    "en": "Strawberry"
+  }
+}