Add application file

Dockerfile

@@ -0,0 +1,20 @@
+# ใช้ Python base image
+FROM python:3.9-slim
+
+# ติดตั้ง dependencies
+WORKDIR /app
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# โหลดโมเดลล่วงหน้า
+COPY download_model.py .
+RUN python download_model.py
+
+# คัดลอกโค้ดทั้งหมด
+COPY . .
+
+# เปิดพอร์ต 7860 สำหรับ Gradio
+EXPOSE 7860
+
+# คำสั่งรัน FastAPI หรือ Gradio
+CMD ["python", "interface.py"]

README.md

@@ -8,4 +8,29 @@ pinned: false
 short_description: baby cry classification
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Baby Cry Detector - Hugging Face Space
+
+## 📝 รายละเอียดโปรเจค
+โมเดลนี้ใช้ **DistilHuBERT** ที่ fine-tune เพื่อแยกเสียงร้องของเด็กทารกจากเสียงอื่น ๆ  
+สามารถใช้งานผ่าน API (**FastAPI**) หรือ **Gradio** UI  
+
+## 🚀 วิธีใช้งาน
+1. **ผ่าน Gradio UI:**  
+   - อัปโหลดไฟล์เสียง และดูผลการจำแนก  
+
+2. **ผ่าน FastAPI:**  
+   - รัน API โดยใช้คำสั่ง  
+     ```
+     uvicorn app:app --host 0.0.0.0 --port 7860
+     ```
+   - ส่ง request ไปยัง  
+     ```
+     POST http://localhost:7860/predict
+     ```
+
+## 📡 Deploy บน Hugging Face Spaces
+1. สร้าง Spaces ใหม่
+2. เลือก **Docker-based app**
+3. อัปโหลด repository นี้ไปที่ Spaces  
+4. รอการ Build และ Deploy  
+5. ใช้งานได้เลย!

app.py

@@ -0,0 +1,28 @@
+from fastapi import FastAPI, File, UploadFile
+from fastapi.responses import JSONResponse
+from transformers import pipeline
+import uvicorn
+import tempfile
+
+app = FastAPI()
+
+# โหลดโมเดล (ใช้ CPU เท่านั้น)
+classifier = pipeline("audio-classification", 
+                      model="AmeerHesham/distilhubert-finetuned-baby_cry", 
+                      device=-1)
+
+@app.post("/predict")
+async def predict_audio(file: UploadFile = File(...)):
+    try:
+        contents = await file.read()
+        with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tmp:
+            tmp.write(contents)
+            tmp_path = tmp.name
+
+        results = classifier(tmp_path)
+        return JSONResponse(content={"results": results})
+    except Exception as e:
+        return JSONResponse(content={"error": str(e)}, status_code=500)
+
+if __name__ == "__main__":
+    uvicorn.run("app:app", host="0.0.0.0", port=7860, reload=True)

download_model.py

@@ -0,0 +1,5 @@
+from transformers import pipeline
+
+print("Downloading pre-trained model...")
+classifier = pipeline("audio-classification", model="AmeerHesham/distilhubert-finetuned-baby_cry")
+print("Model downloaded successfully!")

interface.py

@@ -0,0 +1,26 @@
+import gradio as gr
+from transformers import pipeline
+import tempfile
+
+# โหลดโมเดลล่วงหน้า
+classifier = pipeline("audio-classification", 
+                      model="AmeerHesham/distilhubert-finetuned-baby_cry", 
+                      device=-1)
+
+# ฟังก์ชันสำหรับรัน Gradio
+def classify_audio(audio):
+    with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tmp:
+        tmp.write(audio[1])
+        tmp_path = tmp.name
+    result = classifier(tmp_path)
+    return result
+
+# สร้างอินเทอร์เฟซ
+iface = gr.Interface(fn=classify_audio, 
+                     inputs=gr.Audio(source="upload", type="file"), 
+                     outputs="json",
+                     title="Baby Cry Detector",
+                     description="Upload an audio file to classify whether it contains a baby's cry.")
+
+# รันแอป
+iface.launch()

luna-cry-detection.ipynb

@@ -0,0 +1,120 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "5b8f8811-e9ef-4607-ab97-1f1ca28d370a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: transformers in /Users/zinatip/miniconda3/lib/python3.11/site-packages (4.37.2)\n",
+      "Requirement already satisfied: torchaudio in /Users/zinatip/miniconda3/lib/python3.11/site-packages (2.2.0.dev20240131)\n",
+      "Requirement already satisfied: filelock in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from transformers) (3.13.1)\n",
+      "Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from transformers) (0.28.1)\n",
+      "Requirement already satisfied: numpy>=1.17 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from transformers) (1.26.3)\n",
+      "Requirement already satisfied: packaging>=20.0 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from transformers) (24.1)\n",
+      "Requirement already satisfied: pyyaml>=5.1 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from transformers) (6.0.1)\n",
+      "Requirement already satisfied: regex!=2019.12.17 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from transformers) (2024.11.6)\n",
+      "Requirement already satisfied: requests in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from transformers) (2.32.3)\n",
+      "Requirement already satisfied: tokenizers<0.19,>=0.14 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from transformers) (0.15.1)\n",
+      "Requirement already satisfied: safetensors>=0.4.1 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from transformers) (0.4.2)\n",
+      "Requirement already satisfied: tqdm>=4.27 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from transformers) (4.65.0)\n",
+      "Requirement already satisfied: torch==2.3.0.dev20240131 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from torchaudio) (2.3.0.dev20240131)\n",
+      "Requirement already satisfied: typing-extensions>=4.8.0 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from torch==2.3.0.dev20240131->torchaudio) (4.12.2)\n",
+      "Requirement already satisfied: sympy in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from torch==2.3.0.dev20240131->torchaudio) (1.12)\n",
+      "Requirement already satisfied: networkx in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from torch==2.3.0.dev20240131->torchaudio) (3.2.1)\n",
+      "Requirement already satisfied: jinja2 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from torch==2.3.0.dev20240131->torchaudio) (3.1.4)\n",
+      "Requirement already satisfied: fsspec in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from torch==2.3.0.dev20240131->torchaudio) (2023.12.2)\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from requests->transformers) (2.0.4)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from requests->transformers) (3.4)\n",
+      "Requirement already satisfied: urllib3<3,>=1.21.1 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from requests->transformers) (2.0.0)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from requests->transformers) (2023.11.17)\n",
+      "Requirement already satisfied: MarkupSafe>=2.0 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from jinja2->torch==2.3.0.dev20240131->torchaudio) (2.1.4)\n",
+      "Requirement already satisfied: mpmath>=0.19 in /Users/zinatip/miniconda3/lib/python3.11/site-packages (from sympy->torch==2.3.0.dev20240131->torchaudio) (1.3.0)\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install transformers torchaudio"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "ae2a06e5-6325-4c0b-bc34-3af09e4968b6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/zinatip/miniconda3/lib/python3.11/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import pipeline\n",
+    "\n",
+    "# โหลด pipeline สำหรับ audio classification พร้อมกับโมเดลที่ต้องการ\n",
+    "classifier = pipeline(\"audio-classification\", model=\"AmeerHesham/distilhubert-finetuned-baby_cry\")\n",
+    "\n",
+    "# ระบุ path ของไฟล์เสียง (.wav หรือรูปแบบอื่นๆ ที่รองรับ)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "92d9e206-537b-42d7-b3ee-c76f589cb3a5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[{'score': 0.9975179433822632, 'label': 'hungry'}, {'score': 0.002165452344343066, 'label': 'discomfort'}, {'score': 0.00031626736745238304, 'label': 'tired'}, {'score': 3.506626171656535e-07, 'label': 'belly_pain'}, {'score': 2.5131891234764225e-08, 'label': 'burping'}]\n"
+     ]
+    }
+   ],
+   "source": [
+    "audio_file = \"/Users/zinatip/project/cry-detection/sample.wav\"\n",
+    "# https://huggingface.co/datasets/Nooon/Donate_a_cry/tree/main/belly_pain\n",
+    "\n",
+    "results = classifier(audio_file)\n",
+    "print(results)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1e14e3f3-b2a7-44c6-9029-cf9b49afbef8",
+   "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": "3.11.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn
+gradio
+transformers
+torchaudio
+torch