change prefix length

.ipynb_checkpoints/Untitled-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Untitled.ipynb

@@ -0,0 +1,150 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f3def174",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: gradio in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (3.13.1)\n",
+      "Requirement already satisfied: h11<0.13,>=0.11 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (0.12.0)\n",
+      "Requirement already satisfied: pyyaml in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (6.0)\n",
+      "Requirement already satisfied: httpx in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (0.23.3)\n",
+      "Requirement already satisfied: numpy in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (1.21.6)\n",
+      "Requirement already satisfied: matplotlib in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (3.5.3)\n",
+      "Requirement already satisfied: pillow in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (9.4.0)\n",
+      "Requirement already satisfied: altair in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (4.2.0)\n",
+      "Requirement already satisfied: fsspec in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (2023.1.0)\n",
+      "Requirement already satisfied: jinja2 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (3.1.2)\n",
+      "Requirement already satisfied: pydantic in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (1.10.4)\n",
+      "Requirement already satisfied: ffmpy in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (0.3.0)\n",
+      "Requirement already satisfied: pydub in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (0.25.1)\n",
+      "Requirement already satisfied: python-multipart in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (0.0.5)\n",
+      "Requirement already satisfied: markdown-it-py[linkify,plugins] in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (2.1.0)\n",
+      "Requirement already satisfied: websockets>=10.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (10.4)\n",
+      "Requirement already satisfied: aiohttp in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (3.8.3)\n",
+      "Requirement already satisfied: uvicorn in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (0.20.0)\n",
+      "Requirement already satisfied: pandas in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (1.3.5)\n",
+      "Requirement already satisfied: orjson in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (3.8.5)\n",
+      "Requirement already satisfied: fastapi in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (0.89.1)\n",
+      "Requirement already satisfied: requests in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (2.28.2)\n",
+      "Requirement already satisfied: pycryptodome in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from gradio) (3.16.0)\n",
+      "Requirement already satisfied: typing-extensions>=3.7.4 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from aiohttp->gradio) (4.4.0)\n",
+      "Requirement already satisfied: yarl<2.0,>=1.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from aiohttp->gradio) (1.8.2)\n",
+      "Requirement already satisfied: asynctest==0.13.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from aiohttp->gradio) (0.13.0)\n",
+      "Requirement already satisfied: aiosignal>=1.1.2 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from aiohttp->gradio) (1.3.1)\n",
+      "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from aiohttp->gradio) (4.0.2)\n",
+      "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from aiohttp->gradio) (2.1.1)\n",
+      "Requirement already satisfied: multidict<7.0,>=4.5 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from aiohttp->gradio) (6.0.4)\n",
+      "Requirement already satisfied: attrs>=17.3.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from aiohttp->gradio) (22.2.0)\n",
+      "Requirement already satisfied: frozenlist>=1.1.1 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from aiohttp->gradio) (1.3.3)\n",
+      "Requirement already satisfied: toolz in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from altair->gradio) (0.12.0)\n",
+      "Requirement already satisfied: entrypoints in /usr/local/Cellar/ipython/8.3.0/libexec/lib/python3.10/site-packages (from altair->gradio) (0.4)\n",
+      "Requirement already satisfied: jsonschema>=3.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from altair->gradio) (4.17.3)\n",
+      "Requirement already satisfied: pytz>=2017.3 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from pandas->gradio) (2022.7.1)\n",
+      "Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/Cellar/ipython/8.3.0/libexec/lib/python3.10/site-packages (from pandas->gradio) (2.8.2)\n",
+      "Requirement already satisfied: starlette==0.22.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from fastapi->gradio) (0.22.0)\n",
+      "Requirement already satisfied: anyio<5,>=3.4.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from starlette==0.22.0->fastapi->gradio) (3.6.2)\n",
+      "Requirement already satisfied: sniffio in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from httpx->gradio) (1.3.0)\n",
+      "Requirement already satisfied: rfc3986[idna2008]<2,>=1.3 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from httpx->gradio) (1.5.0)\n",
+      "Requirement already satisfied: certifi in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from httpx->gradio) (2022.12.7)\n",
+      "Requirement already satisfied: httpcore<0.17.0,>=0.15.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from httpx->gradio) (0.15.0)\n",
+      "Requirement already satisfied: MarkupSafe>=2.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from jinja2->gradio) (2.1.2)\n",
+      "Requirement already satisfied: mdurl~=0.1 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from markdown-it-py[linkify,plugins]->gradio) (0.1.2)\n",
+      "Requirement already satisfied: mdit-py-plugins in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from markdown-it-py[linkify,plugins]->gradio) (0.3.3)\n",
+      "Requirement already satisfied: linkify-it-py~=1.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from markdown-it-py[linkify,plugins]->gradio) (1.0.3)\n",
+      "Requirement already satisfied: cycler>=0.10 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from matplotlib->gradio) (0.11.0)\n",
+      "Requirement already satisfied: fonttools>=4.22.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from matplotlib->gradio) (4.38.0)\n",
+      "Requirement already satisfied: pyparsing>=2.2.1 in /usr/local/Cellar/ipython/8.3.0/libexec/lib/python3.10/site-packages (from matplotlib->gradio) (3.0.8)\n",
+      "Requirement already satisfied: packaging>=20.0 in /usr/local/Cellar/ipython/8.3.0/libexec/lib/python3.10/site-packages (from matplotlib->gradio) (21.3)\n",
+      "Requirement already satisfied: kiwisolver>=1.0.1 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from matplotlib->gradio) (1.4.4)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: six>=1.4.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from python-multipart->gradio) (1.16.0)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from requests->gradio) (3.4)\n",
+      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from requests->gradio) (1.26.14)\n",
+      "Requirement already satisfied: click>=7.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from uvicorn->gradio) (8.1.3)\n",
+      "Requirement already satisfied: importlib-metadata in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from click>=7.0->uvicorn->gradio) (6.0.0)\n",
+      "Requirement already satisfied: importlib-resources>=1.4.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from jsonschema>=3.0->altair->gradio) (5.10.2)\n",
+      "Requirement already satisfied: pyrsistent!=0.17.0,!=0.17.1,!=0.17.2,>=0.14.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from jsonschema>=3.0->altair->gradio) (0.19.3)\n",
+      "Requirement already satisfied: pkgutil-resolve-name>=1.3.10 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from jsonschema>=3.0->altair->gradio) (1.3.10)\n",
+      "Requirement already satisfied: uc-micro-py in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from linkify-it-py~=1.0->markdown-it-py[linkify,plugins]->gradio) (1.0.1)\n",
+      "Requirement already satisfied: zipp>=3.1.0 in /Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/lib/python3.7/site-packages (from importlib-resources>=1.4.0->jsonschema>=3.0->altair->gradio) (3.11.0)\n",
+      "\u001b[33mWARNING: You are using pip version 22.0.2; however, version 22.3.1 is available.\n",
+      "You should consider upgrading via the '/Users/sheonhan/.pyenv/versions/3.7.9/envs/language-demo/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n",
+      "\u001b[0m"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install gradio"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "25f4c73e",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'gradio'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "Input \u001b[0;32mIn [4]\u001b[0m, in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mgradio\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mgr\u001b[39;00m\n\u001b[1;32m      3\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mgreet\u001b[39m(name):\n\u001b[1;32m      4\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mHello \u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m name \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m!\u001b[39m\u001b[38;5;124m\"\u001b[39m\n",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'gradio'"
+     ]
+    }
+   ],
+   "source": [
+    "import gradio as gr\n",
+    "\n",
+    "def greet(name):\n",
+    "    return \"Hello \" + name + \"!\"\n",
+    "\n",
+    "demo = gr.Interface(fn=greet, inputs=\"text\", outputs=\"text\")\n",
+    "\n",
+    "demo.launch() "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a740eff3",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

app.py

@@ -36,7 +36,7 @@ def identify_language(text):
     model = fasttext.load_model(model_full_path)
     predictions = model.predict(text, k=1) # e.g., (('__label__eng_Latn',), array([0.81148803]))
     
-    PREFIX_LENGTH = 7 # To strip away '__label__' from language code
+    PREFIX_LENGTH = 9 # To strip away '__label__' from language code
     language_code = predictions[0][0][PREFIX_LENGTH:]
     return language_code