Duplicate from Omnibus/Translate-100

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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 +1,14 @@
+---
+title: Translate 100
+emoji: >-
+  👭👩🏻‍🤝‍👩🏻👩🏼‍🤝‍👩🏻👩🏼‍🤝‍👩🏼👩🏽‍🤝‍👩🏻👩🏽‍🤝‍👩🏼👩🏽‍🤝‍👩🏽👩🏾‍🤝‍👩🏻👩🏾‍🤝‍👩🏼👩🏾‍🤝‍👩🏽👫👩🏻‍🤝‍🧑🏻👩🏼‍🤝‍🧑🏾👩🏼‍🤝‍🧑🏼👩🏻‍🤝‍🧑🏽👩🏻‍🤝‍🧑🏾👩🏿‍🤝‍👩🏽
+colorFrom: gray
+colorTo: blue
+sdk: gradio
+sdk_version: 3.17.0
+app_file: app.py
+pinned: true
+duplicated_from: Omnibus/Translate-100
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,154 @@
+import gradio as gr
+import os
+import torch
+import gradio as gr
+from transformers import M2M100Tokenizer, M2M100ForConditionalGeneration
+
+if torch.cuda.is_available():
+    device = torch.device("cuda:0")
+else:
+    device = torch.device("cpu")
+
+tokenizer = M2M100Tokenizer.from_pretrained("facebook/m2m100_1.2B")
+model = M2M100ForConditionalGeneration.from_pretrained("facebook/m2m100_1.2B").to(device)
+model.eval()
+
+lang_id = {
+    "":"",
+    "Afrikaans": "af",
+    "Albanian": "sq",
+    "Amharic": "am",
+    "Arabic": "ar",
+    "Armenian": "hy",
+    "Asturian": "ast",
+    "Azerbaijani": "az",
+    "Bashkir": "ba",
+    "Belarusian": "be",
+    "Bulgarian": "bg",
+    "Bengali": "bn",
+    "Breton": "br",
+    "Bosnian": "bs",
+    "Burmese": "my",
+    "Catalan": "ca",
+    "Cebuano": "ceb",
+    "Chinese": "zh",
+    "Chinese (simplified)": "zh",
+    "Chinese (traditional)": "zh",    
+    "Croatian": "hr",
+    "Czech": "cs",
+    "Danish": "da",
+    "Dutch": "nl",
+    "English": "en",
+    "Estonian": "et",
+    "Fulah": "ff",
+    "Finnish": "fi",
+    "French": "fr",
+    "Western Frisian": "fy",
+    "Gaelic": "gd",
+    "Galician": "gl",
+    "Georgian": "ka",
+    "German": "de",
+    "Greek": "el",
+    "Gujarati": "gu",
+    "Hausa": "ha",
+    "Hebrew": "he",
+    "Hindi": "hi",
+    "Haitian": "ht",
+    "Hungarian": "hu",
+    "Irish": "ga",
+    "Indonesian": "id",
+    "Igbo": "ig",
+    "Iloko": "ilo",
+    "Icelandic": "is",
+    "Italian": "it",
+    "Japanese": "ja",
+    "Javanese": "jv",
+    "Kazakh": "kk",
+    "Central Khmer": "km",
+    "Kannada": "kn",
+    "Korean": "ko",
+    "Luxembourgish": "lb",
+    "Ganda": "lg",
+    "Lingala": "ln",
+    "Lao": "lo",
+    "Lithuanian": "lt",
+    "Latvian": "lv",
+    "Malagasy": "mg",
+    "Macedonian": "mk",
+    "Malayalam": "ml",
+    "Mongolian": "mn",
+    "Marathi": "mr",
+    "Malay": "ms",
+    "Nepali": "ne",
+    "Norwegian": "no",
+    "Northern Sotho": "ns",
+    "Occitan": "oc",
+    "Oriya": "or",
+    "Panjabi": "pa",
+    "Persian": "fa",
+    "Polish": "pl",
+    "Pushto": "ps",
+    "Portuguese": "pt",
+    "Romanian": "ro",
+    "Russian": "ru",
+    "Sindhi": "sd",
+    "Sinhala": "si",
+    "Slovak": "sk",
+    "Slovenian": "sl",
+    "Spanish": "es",
+    "Somali": "so",
+    "Serbian": "sr",
+    "Serbian (cyrillic)": "sr",
+    "Serbian (latin)": "sr",    
+    "Swati": "ss",
+    "Sundanese": "su",
+    "Swedish": "sv",
+    "Swahili": "sw",
+    "Tamil": "ta",
+    "Thai": "th",
+    "Tagalog": "tl",
+    "Tswana": "tn",
+    "Turkish": "tr",
+    "Ukrainian": "uk",
+    "Urdu": "ur",
+    "Uzbek": "uz",
+    "Vietnamese": "vi",
+    "Welsh": "cy",
+    "Wolof": "wo",
+    "Xhosa": "xh",
+    "Yiddish": "yi",
+    "Yoruba": "yo",
+    "Zulu": "zu",
+}
+
+def trans_to(input,src,trg):
+    src_lang = lang_id[src]
+    trg_lang = lang_id[trg]
+    if trg_lang != src_lang:
+        tokenizer.src_lang = src_lang
+        with torch.no_grad():
+            encoded_input = tokenizer(input, return_tensors="pt").to(device)
+            generated_tokens = model.generate(**encoded_input, forced_bos_token_id=tokenizer.get_lang_id(trg_lang))
+            translated_text = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]
+    else:
+        translated_text=input
+        pass
+    return translated_text
+
+with gr.Blocks() as transbot:
+    with gr.Row():
+        gr.Column()
+        with gr.Column():
+            gr.Markdown("""<h1><center>Translate - 100 Languages</center></h1><h4><center>Translation may not be accurate</center></h4>""")
+            with gr.Row():
+                lang_from = gr.Dropdown(label="From:", choices=list(lang_id.keys()),value="English")
+                lang_to = gr.Dropdown(label="To:", choices=list(lang_id.keys()),value="Chinese")
+            submit = gr.Button("Go")
+            with gr.Row():
+                with gr.Column():
+                    message = gr.Textbox(label="Prompt",placeholder="Enter Prompt",lines=4)
+                    translated = gr.Textbox(label="Translated",lines=4,interactive=False)
+        gr.Column()
+    submit.click(trans_to, inputs=[message,lang_from,lang_to], outputs=[translated])
+transbot.queue(concurrency_count=20)
+transbot.launch()

requirements.txt

@@ -0,0 +1,3 @@
+torch
+transformers
+transformers[sentencepiece]