Duplicate from Omnibus/detect-language

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,13 @@
+---
+title: Detect Language
+emoji: 🌍
+colorFrom: red
+colorTo: green
+sdk: gradio
+sdk_version: 3.42.0
+app_file: app.py
+pinned: false
+duplicated_from: Omnibus/detect-language
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,117 @@
+import gradio as gr
+import easyocr
+import numpy as np
+from PIL import Image
+
+
+
+ocr_id = {
+    "Afrikaans": "af",
+    "Albanian": "sq",
+    "Arabic": "ar",
+    "Azerbaijani": "az",
+    "Belarusian": "be",
+    "Bulgarian": "bg",
+    "Bengali": "bn",
+    "Bosnian": "bs",
+    "Chinese (simplified)": "ch_sim",
+    "Chinese (traditional)": "ch_tra",
+    "Croatian": "hr",
+    "Czech": "cs",
+    "Danish": "da",
+    "Dutch": "nl",
+    "English": "en",
+    "Estonian": "et",
+    "French": "fr",
+    "German": "de",
+    "Irish": "ga",
+    "Hindi": "hi",
+    "Hungarian": "hu",
+    "Indonesian": "id",
+    "Icelandic": "is",
+    "Italian": "it",
+    "Japanese": "ja",
+    "Kannada": "kn",
+    "Korean": "ko",
+    "Lithuanian": "lt",
+    "Latvian": "lv",
+    "Mongolian": "mn",
+    "Marathi": "mr",
+    "Malay": "ms",
+    "Nepali": "ne",
+    "Norwegian": "no",
+    "Occitan": "oc",
+    "Polish": "pl",
+    "Portuguese": "pt",
+    "Romanian": "ro",
+    "Russian": "ru",
+    "Serbian (cyrillic)": "rs_cyrillic",
+    "Serbian (latin)": "rs_latin",
+    "Slovak": "sk",
+    "Slovenian": "sl",
+    "Spanish": "es",
+    "Swedish": "sv",
+    "Swahili": "sw",
+    "Tamil": "ta",
+    "Thai": "th",
+    "Tagalog": "tl",
+    "Turkish": "tr",
+    "Ukrainian": "uk",
+    "Urdu": "ur",
+    "Uzbek": "uz",
+    "Vietnamese": "vi",
+    "Welsh": "cy",
+    "Zulu": "zu",
+}
+
+def detect_lang(img,conf,blength=200):
+    targ = 0
+    ser_len=len(ocr_id)
+    #targ =[]
+    img = Image.open(img)
+    img1 = np.array(img)
+    #keyd = ocr_id.keys()
+    numb=0
+    mylist = []
+    for key in ocr_id.keys():
+        mylist.append(key)
+    for numb, key in enumerate(mylist):
+    #for i,keyp in enumerate(keyd):
+        #keyp = keyd[key]
+        try:
+            lang=[f"{ocr_id[mylist[numb]]}"]
+            #lang=value
+            #img.thumbnail((1000,1000), Image.Resampling.LANCZOS)
+            #path = f"/tmp/{uuid.uuid4()}.jpg"
+            #img.save(path)
+            reader = easyocr.Reader(lang)
+            bounds = reader.readtext(img1)
+            print (f'{bounds[0][1]} = {bounds[0][2]}')
+    
+            if len(bounds) > blength:
+                return print(f"Max Bounds Exceed, bounds={len(bounds)}")
+            else:
+                pass
+            if bounds[0][2] > targ:
+                targ = bounds[0][2]
+                
+                out = (f'{keyp} = Confidence: {bounds[0][2]}')
+            #numb+=1
+            if numb>=ser_len:
+                return out
+            if targ >=75:
+                return out            
+        except Exception:
+        
+            pass
+
+with gr.Blocks() as app:
+
+    im = gr.Image(type = "filepath")
+    ocr_sens=gr.Slider(0.1, 1, step=0.05,value=0.25,label="Detect Min Confidence")
+    max_tok=gr.Number(label="Max Tokens",step=1, value=200)
+    det_btn = gr.Button()
+    det_out = gr.Markdown("""""")
+
+    det_btn.click(detect_lang,[im,ocr_sens,],det_out)
+app.launch()

requirements.txt

@@ -0,0 +1 @@
+easyocr