{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":121150,"databundleVersionId":15061024,"sourceType":"competition"},{"sourceId":723801,"sourceType":"modelInstanceVersion","isSourceIdPinned":true,"modelInstanceId":550779,"modelId":563404}],"dockerImageVersionId":31234,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import os\nimport re\nimport unicodedata\nimport pandas as pd\nimport torch\nfrom torch.utils.data import Dataset, DataLoader\nfrom tqdm.auto import tqdm\nfrom transformers import AutoTokenizer, AutoModelForSeq2SeqLM\n\n# --- CONFIGURATION ---\nTEST_PATH = \"/kaggle/input/deep-past-initiative-machine-translation/test.csv\"\nMODEL_PATH = \"/kaggle/input/byt5-small/transformers/default/1\" \n\nBATCH_SIZE = 20   # Safe inference batch size\nMAX_LENGTH = 384  # Must match training length\nDEVICE = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n\n# --- CLEANING FUNCTION (Must match training!) ---\ndef clean_text(text):\n    if pd.isna(text): return \"\"\n    text = str(text)\n    text = unicodedata.normalize('NFC', text)\n    text = text.replace(\"…\", \"...\")\n    text = re.sub(r'\\.\\s*\\.\\s*\\.', '...', text)\n    text = text.replace('“', '\"').replace('”', '\"')\n    text = re.sub(r'\\s+', ' ', text).strip()\n    return text\n\nprint(f\"Loading model from {MODEL_PATH}...\")\n\ntokenizer = AutoTokenizer.from_pretrained('/kaggle/input/byt5-small/transformers/default/1', local_files_only=True)\nmodel = AutoModelForSeq2SeqLM.from_pretrained('/kaggle/input/byt5-small/transformers/default/1', local_files_only=True)\nmodel = model.to(DEVICE)\nmodel.eval()\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class InferenceDataset(Dataset):\n    def __init__(self, df, tokenizer):\n        self.texts = [clean_text(t) for t in df['transliteration']]\n        # Add prefix\n        self.texts = [\"translate Akkadian to English: \" + t for t in self.texts]\n        self.tokenizer = tokenizer\n        self.ids = df['id'].tolist()\n        \n    def __len__(self):\n        return len(self.texts)\n    \n    def __getitem__(self, idx):\n        text = self.texts[idx]\n        inputs = self.tokenizer(\n            text, \n            padding=\"max_length\", \n            truncation=True, \n            max_length=MAX_LENGTH, \n            return_tensors=\"pt\"\n        )\n        return {\n            \"input_ids\": inputs[\"input_ids\"].squeeze(0),\n            \"attention_mask\": inputs[\"attention_mask\"].squeeze(0),\n            \"id\": self.ids[idx]\n        }\n\n\ntest_df = pd.read_csv(TEST_PATH)\ntest_dataset = InferenceDataset(test_df, tokenizer)\ntest_loader = DataLoader(test_dataset, batch_size=BATCH_SIZE, shuffle=False)\n\nall_predictions = []\nall_ids = []\n\nprint(f\"Starting Inference on {len(test_df)} rows...\")\n\nwith torch.no_grad():\n    for batch in tqdm(test_loader):\n        input_ids = batch[\"input_ids\"].to(DEVICE)\n        attention_mask = batch[\"attention_mask\"].to(DEVICE)\n        \n        \n        outputs = model.generate(\n            input_ids=input_ids,\n            attention_mask=attention_mask,\n            max_length=MAX_LENGTH,\n            num_beams=5,\n            early_stopping=True\n        )\n        \n        decoded = tokenizer.batch_decode(outputs, skip_special_tokens=True)\n        all_predictions.extend([d.strip() for d in decoded])\n        all_ids.extend(batch[\"id\"].tolist())\n\nprint(\"Inference Complete.\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-18T10:39:28.145860Z","iopub.execute_input":"2026-01-18T10:39:28.146087Z","execution_failed":"2026-01-18T10:39:29.973Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\nsubmission = pd.DataFrame({\n    \"id\": all_ids,\n    \"translation\": all_predictions\n})\n\n\nsubmission[\"translation\"] = submission[\"translation\"].apply(lambda x: x if len(x) > 0 else \"...\")\n\nsubmission.to_csv(\"submission.csv\", index=False)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-16T06:04:56.990451Z","iopub.execute_input":"2026-01-16T06:04:56.990887Z","iopub.status.idle":"2026-01-16T06:04:57.016916Z","shell.execute_reply.started":"2026-01-16T06:04:56.990858Z","shell.execute_reply":"2026-01-16T06:04:57.015461Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}