ok

.gitea/workflow/build.yaml

@@ -0,0 +1,48 @@
+name: Build
+run-name: ${{ github.actor }} is upgrade release 🚀
+on: [push]
+env:
+  REPOSITORY: ${{ github.repository }}
+  COMMIT_ID: ${{ github.sha }}
+jobs:
+  Build-Deploy-Actions:
+    runs-on: ubuntu-latest
+    steps:
+      - run: echo "🎉 The job was automatically triggered by a ${{ github.event_name }} event."
+      - run: echo "🐧 This job is now running on a ${{ runner.os }} server hosted by Gitea!"
+      - run: echo "🔎 The name of your branch is ${{ github.ref }} and your repository is ${{ github.repository }}."
+      - name: Check out repository code
+        uses: actions/checkout@v3
+      -
+        name: Setup Git LFS
+        run: |
+          git lfs install
+          git lfs fetch
+          git lfs checkout                              
+      - name: List files in the repository
+        run: |
+                                                                                ls ${{ github.workspace }}
+      -
+        name: Docker Image Info
+        id: image-info
+        run: |
+          echo "::set-output name=image_name::$(echo $REPOSITORY | tr '[:upper:]' '[:lower:]')"
+          echo "::set-output name=image_tag::${COMMIT_ID:0:10}"                              
+      -
+        name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          registry: artifacts.iflytek.com
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      -
+        name: Build and push
+        run: |
+          docker version
+          docker buildx build -t artifacts.iflytek.com/docker-private/atp/${{ steps.image-info.outputs.image_name }}:${{ steps.image-info.outputs.image_tag }} . --file ${{ github.workspace }}/Dockerfile --load
+          docker push artifacts.iflytek.com/docker-private/atp/${{ steps.image-info.outputs.image_name }}:${{ steps.image-info.outputs.image_tag }}
+          docker rmi artifacts.iflytek.com/docker-private/atp/${{ steps.image-info.outputs.image_name }}:${{ steps.image-info.outputs.image_tag }}                              
+      - run: echo "🍏 This job's status is ${{ job.status }}."
+

Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3.8.13
+
+WORKDIR /app
+
+COPY . /app
+
+RUN pip config set global.index-url https://pypi.mirrors.ustc.edu.cn/simple 
+RUN pip install -r requirements.txt
+
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,60 @@
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+from languages import LANGUANGE_MAP
+import gradio as gr
+import torch
+from gradio.themes.utils import sizes
+
+#model_ckpt = "ivanlau/language-detection-fine-tuned-on-xlm-roberta-base"
+model_ckpt = "papluca/xlm-roberta-base-language-detection"
+model = AutoModelForSequenceClassification.from_pretrained(model_ckpt)
+tokenizer = AutoTokenizer.from_pretrained(model_ckpt)
+
+theme = gr.themes.Default(radius_size=sizes.radius_none).set(
+    block_label_text_color = '#4D63FF',
+    block_title_text_color = '#4D63FF',
+    button_primary_text_color = '#4D63FF',
+    button_primary_background_fill='#FFFFFF',
+    button_primary_border_color='#4D63FF',
+    button_primary_background_fill_hover='#EDEFFF',
+)
+
+
+def detect_language(sentence):
+    tokenized_sentence = tokenizer(sentence, return_tensors='pt')
+    output = model(**tokenized_sentence)
+    predictions = torch.nn.functional.softmax(output.logits, dim=-1)
+    _, preds = torch.max(predictions, dim=-1)
+    return LANGUANGE_MAP[preds.item()]
+
+examples = [
+    "恭喜发财!",
+    "Jumpa lagi, saya pergi kerja.",
+    "你食咗飯未呀?",
+    "もう食べましたか?",
+    "as-tu mangé",
+    "أريد أن ألعب كرة الريشة"
+]
+
+inputs=gr.inputs.Textbox(placeholder="Enter your text here", label="Text content", lines=5)
+outputs=gr.outputs.Label(label="Language detected:")
+article = """
+Fine-tuned on xlm-roberta-base model.\n
+Supported languages:\n 
+    'Arabic', 'Basque', 'Breton', 'Catalan', 'Chinese_China', 'Chinese_Hongkong', 'Chinese_Taiwan', 'Chuvash', 'Czech', 
+    'Dhivehi', 'Dutch', 'English', 'Esperanto', 'Estonian', 'French', 'Frisian', 'Georgian', 'German', 'Greek', 'Hakha_Chin', 
+    'Indonesian', 'Interlingua', 'Italian', 'Japanese', 'Kabyle', 'Kinyarwanda', 'Kyrgyz', 'Latvian', 'Maltese', 
+    'Mangolian', 'Persian', 'Polish', 'Portuguese', 'Romanian', 'Romansh_Sursilvan', 'Russian', 'Sakha', 'Slovenian', 
+    'Spanish', 'Swedish', 'Tamil', 'Tatar', 'Turkish', 'Ukranian', 'Welsh'
+"""
+
+gr.Interface(
+    fn=detect_language,
+    inputs=inputs,
+    outputs=outputs,
+    verbose=True,
+    examples = examples,
+    title="Language Detector 🔠",
+    description="A simple interface to detect 45 languages.",
+    article=article,
+    theme=theme
+).launch()

languages.py

@@ -0,0 +1,47 @@
+LANGUANGE_MAP = {
+    0: 'Arabic',
+    1: 'Basque',
+    2: 'Breton',
+    3: 'Catalan',
+    4: 'Chinese_China',
+    5: 'Chinese_Hongkong',
+    6: 'Chinese_Taiwan',
+    7: 'Chuvash',
+    8: 'Czech',
+    9: 'Dhivehi',
+    10: 'Dutch',
+    11: 'English',
+    12: 'Esperanto',
+    13: 'Estonian',
+    14: 'French',
+    15: 'Frisian',
+    16: 'Georgian',
+    17: 'German',
+    18: 'Greek',
+    19: 'Hakha_Chin',
+    20: 'Indonesian',
+    21: 'Interlingua',
+    22: 'Italian',
+    23: 'Japanese',
+    24: 'Kabyle',
+    25: 'Kinyarwanda',
+    26: 'Kyrgyz',
+    27: 'Latvian',
+    28: 'Maltese',
+    29: 'Mongolian',
+    30: 'Persian',
+    31: 'Polish',
+    32: 'Portuguese',
+    33: 'Romanian',
+    34: 'Romansh_Sursilvan',
+    35: 'Russian',
+    36: 'Sakha',
+    37: 'Slovenian',
+    38: 'Spanish',
+    39: 'Swedish',
+    40: 'Tamil',
+    41: 'Tatar',
+    42: 'Turkish',
+    43: 'Ukranian',
+    44: 'Welsh'
+ }

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+transformers
+torch