update

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.xlsx filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+*.jit filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,15 @@
+
+.git/
+.idea/
+
+#data/
+#pretrained_models/
+temp/
+
+**/cache/
+**/__pycache__/
+
+**/*.env
+**/*.mp3
+**/*.png
+**/*.xlsx

Dockerfile

@@ -0,0 +1,30 @@
+# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.8
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --upgrade pip
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+# Set up a new user named "user" with user ID 1000
+RUN useradd -m -u 1000 user
+
+# Switch to the "user" user
+USER user
+
+# Set home to the user's home directory
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+# Set the working directory to the user's home directory
+WORKDIR $HOME/app
+
+# Copy the current directory contents into the container at $HOME/app setting the owner to the user
+COPY --chown=user . $HOME/app
+
+CMD ["python", "main.py"]

lang_id_examples.json

@@ -0,0 +1,12 @@
+[
+  [
+    "你好。",
+    "zh",
+    "langid"
+  ],
+  [
+    "普段使いとバイクに乗るときのブーツ兼用として購入しました。",
+    "ja",
+    "langid"
+  ]
+]

main.py

@@ -0,0 +1,113 @@
+#!/usr/bin/python3
+# -*- coding: utf-8 -*-
+"""
+https://huggingface.co/spaces/sayakpaul/demo-docker-gradio
+"""
+import argparse
+import json
+import platform
+from typing import Tuple
+
+import gradio as gr
+import langid
+from langid.langid import LanguageIdentifier, model
+import matplotlib.pyplot as plt
+import numpy as np
+from PIL import Image
+
+from project_settings import project_path, temp_directory
+
+
+def get_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--lang_id_examples_file",
+        default=(project_path / "lang_id_examples.json").as_posix(),
+        type=str
+    )
+    args = parser.parse_args()
+    return args
+
+
+lang_id_identifier = LanguageIdentifier.from_modelstring(model, norm_probs=True)
+
+
+def click_lang_id_button(text: str, ground_true: str, model_name: str):
+    global lang_id_identifier
+
+    if model_name == "langid":
+        label, prob = lang_id_identifier.classify(text)
+    else:
+        label = "model_name not available."
+        prob = 0.0
+    return label, round(prob, 4)
+
+
+def main():
+    args = get_args()
+
+    brief_description = """
+    ## Language Identification
+
+    langid 识别 97 种语言。
+    https://github.com/saffsd/langid.py
+    """
+
+    # examples
+    with open(args.lang_id_examples_file, "r", encoding="utf-8") as f:
+        lang_id_examples = json.load(f)
+
+    # ui
+    with gr.Blocks() as blocks:
+        gr.Markdown(value=brief_description)
+
+        with gr.Row():
+            with gr.Column(scale=5):
+                with gr.Tabs():
+                    with gr.TabItem("lang_id"):
+                        gr.Markdown(value="")
+
+                        with gr.Row():
+                            with gr.Column(scale=1):
+                                lang_id_text = gr.Textbox(lines=2, max_lines=50, label="text")
+                                lang_id_ground_true = gr.Textbox(label="ground_true")
+
+                                lang_id_model_name = gr.Dropdown(choices=["langid"], value="langid", label="model_name")
+                                lang_id_button = gr.Button("run", variant="primary")
+
+                            with gr.Column(scale=1):
+                                lang_id_label = gr.Textbox(label="label")
+                                lang_id_prob = gr.Number(label="prob")
+
+                        gr.Examples(
+                            examples=lang_id_examples,
+                            inputs=[
+                                lang_id_text,
+                                lang_id_ground_true,
+                                lang_id_model_name,
+                            ],
+                            outputs=[lang_id_label, lang_id_prob],
+                            fn=click_lang_id_button
+                        )
+
+                        # click event
+                        lang_id_button.click(
+                            click_lang_id_button,
+                            inputs=[
+                                lang_id_text,
+                                lang_id_ground_true,
+                                lang_id_model_name,
+                            ],
+                            outputs=[lang_id_label, lang_id_prob],
+                        )
+
+    blocks.queue().launch(
+        share=False if platform.system() == "Windows" else False,
+        server_name="127.0.0.1" if platform.system() == "Windows" else "0.0.0.0",
+        server_port=7860
+    )
+    return
+
+
+if __name__ == "__main__":
+    main()

project_settings.py

@@ -0,0 +1,16 @@
+#!/usr/bin/python3
+# -*- coding: utf-8 -*-
+import os
+from pathlib import Path
+
+
+project_path = os.path.abspath(os.path.dirname(__file__))
+project_path = Path(project_path)
+
+
+temp_directory = project_path / "temp"
+temp_directory.mkdir(exist_ok=True)
+
+
+if __name__ == '__main__':
+    pass

requirements.txt

@@ -0,0 +1,2 @@
+gradio==4.28.3
+langid==1.1.6