{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"## Import","metadata":{}},{"cell_type":"code","source":"!cp -r ../input/python-packages2 ./\n\n!tar xvfz ./python-packages2/jiwer.tgz\n!pip install ./jiwer/jiwer-2.3.0-py3-none-any.whl -f ./ --no-index\n!tar xvfz ./python-packages2/normalizer.tgz\n!pip install ./normalizer/bnunicodenormalizer-0.0.24.tar.gz -f ./ --no-index\n!tar xvfz ./python-packages2/pyctcdecode.tgz\n!pip install ./pyctcdecode/attrs-22.1.0-py2.py3-none-any.whl -f ./ --no-index --no-deps\n!pip install ./pyctcdecode/exceptiongroup-1.0.0rc9-py3-none-any.whl -f ./ --no-index --no-deps\n!pip install ./pyctcdecode/hypothesis-6.54.4-py3-none-any.whl -f ./ --no-index --no-deps\n!pip install ./pyctcdecode/numpy-1.21.6-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl -f ./ --no-index --no-deps\n!pip install ./pyctcdecode/pygtrie-2.5.0.tar.gz -f ./ --no-index --no-deps\n!pip install ./pyctcdecode/sortedcontainers-2.4.0-py2.py3-none-any.whl -f ./ --no-index --no-deps\n!pip install ./pyctcdecode/pyctcdecode-0.4.0-py2.py3-none-any.whl -f ./ --no-index --no-deps\n\n!tar xvfz ./python-packages2/pypikenlm.tgz\n!pip install ./pypikenlm/pypi-kenlm-0.1.20220713.tar.gz -f ./ --no-index --no-deps","metadata":{"_kg_hide-output":true,"execution":{"iopub.status.busy":"2023-10-18T06:20:36.850161Z","iopub.execute_input":"2023-10-18T06:20:36.851087Z","iopub.status.idle":"2023-10-18T06:21:55.302543Z","shell.execute_reply.started":"2023-10-18T06:20:36.851045Z","shell.execute_reply":"2023-10-18T06:21:55.301482Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import typing as tp\nfrom pathlib import Path\nfrom functools import partial\nfrom dataclasses import dataclass, field\n\nimport pandas as pd\nimport pyctcdecode\nimport numpy as np\nfrom tqdm.notebook import tqdm\n\nimport librosa\n\nimport pyctcdecode\nimport kenlm\nimport torch\nfrom transformers import Wav2Vec2Processor, Wav2Vec2ProcessorWithLM, Wav2Vec2ForCTC\nfrom bnunicodenormalizer import Normalizer\n\nimport cloudpickle as cpkl","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-10-18T06:21:55.304799Z","iopub.execute_input":"2023-10-18T06:21:55.305117Z","iopub.status.idle":"2023-10-18T06:22:09.840707Z","shell.execute_reply.started":"2023-10-18T06:21:55.305091Z","shell.execute_reply":"2023-10-18T06:22:09.839748Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ROOT = Path.cwd().parent\nINPUT = ROOT / \"input\"\nDATA = INPUT / \"bengaliai-speech\"\nTRAIN = DATA / \"train_mp3s\"\nTEST = DATA / \"test_mp3s\"\n\nSAMPLING_RATE = 16_000\nMODEL_PATH = INPUT / \"bengali-v231/out_model/\"\nLM_PATH = INPUT / \"bengali-sr-download-public-trained-models/wav2vec2-xls-r-300m-bengali/language_model/\"","metadata":{"execution":{"iopub.status.busy":"2023-10-18T06:22:09.842225Z","iopub.execute_input":"2023-10-18T06:22:09.842633Z","iopub.status.idle":"2023-10-18T06:22:09.848109Z","shell.execute_reply.started":"2023-10-18T06:22:09.842598Z","shell.execute_reply":"2023-10-18T06:22:09.847308Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Load model, processor, decoder","metadata":{}},{"cell_type":"code","source":"model = Wav2Vec2ForCTC.from_pretrained(MODEL_PATH)\nprocessor = Wav2Vec2Processor.from_pretrained(MODEL_PATH)","metadata":{"execution":{"iopub.status.busy":"2023-10-18T06:22:09.850343Z","iopub.execute_input":"2023-10-18T06:22:09.851026Z","iopub.status.idle":"2023-10-18T06:22:11.097040Z","shell.execute_reply.started":"2023-10-18T06:22:09.850995Z","shell.execute_reply":"2023-10-18T06:22:11.094203Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"vocab_dict = processor.tokenizer.get_vocab()\nsorted_vocab_dict = {k: v for k, v in sorted(vocab_dict.items(), key=lambda item: item[1])}\n\ndecoder = pyctcdecode.build_ctcdecoder(\n    list(sorted_vocab_dict.keys()),\n    str(LM_PATH / \"5gram.bin\"),\n    alpha = 0.5,\n    beta = 0.5,\n)","metadata":{"execution":{"iopub.status.busy":"2023-10-18T06:22:11.098131Z","iopub.status.idle":"2023-10-18T06:22:11.098780Z","shell.execute_reply.started":"2023-10-18T06:22:11.098530Z","shell.execute_reply":"2023-10-18T06:22:11.098550Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"processor_with_lm = Wav2Vec2ProcessorWithLM(\n    feature_extractor=processor.feature_extractor,\n    tokenizer=processor.tokenizer,\n    decoder=decoder\n)","metadata":{"execution":{"iopub.status.busy":"2023-10-18T06:22:11.100241Z","iopub.status.idle":"2023-10-18T06:22:11.100759Z","shell.execute_reply.started":"2023-10-18T06:22:11.100492Z","shell.execute_reply":"2023-10-18T06:22:11.100519Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Prepare dataloader","metadata":{}},{"cell_type":"code","source":"class BengaliSRTestDataset(torch.utils.data.Dataset):\n    \n    def __init__(\n        self,\n        audio_paths: list[str],\n        sampling_rate: int\n    ):\n        self.audio_paths = audio_paths\n        self.sampling_rate = sampling_rate\n        \n    def __len__(self,):\n        return len(self.audio_paths)\n    \n    def __getitem__(self, index: int):\n        audio_path = self.audio_paths[index]\n        sr = self.sampling_rate\n        w = librosa.load(audio_path, sr=sr, mono=False)[0]\n        \n        return w","metadata":{"execution":{"iopub.status.busy":"2023-10-18T06:22:11.102786Z","iopub.status.idle":"2023-10-18T06:22:11.103600Z","shell.execute_reply.started":"2023-10-18T06:22:11.103381Z","shell.execute_reply":"2023-10-18T06:22:11.103400Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test = pd.read_csv(DATA / \"sample_submission.csv\", dtype={\"id\": str})\nprint(test.head())","metadata":{"execution":{"iopub.status.busy":"2023-10-18T06:22:11.104599Z","iopub.status.idle":"2023-10-18T06:22:11.104934Z","shell.execute_reply.started":"2023-10-18T06:22:11.104767Z","shell.execute_reply":"2023-10-18T06:22:11.104782Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_audio_paths = [str(TEST / f\"{aid}.mp3\") for aid in test[\"id\"].values]","metadata":{"execution":{"iopub.status.busy":"2023-10-18T06:22:11.106343Z","iopub.status.idle":"2023-10-18T06:22:11.106672Z","shell.execute_reply.started":"2023-10-18T06:22:11.106522Z","shell.execute_reply":"2023-10-18T06:22:11.106537Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_dataset = BengaliSRTestDataset(\n    test_audio_paths, SAMPLING_RATE\n)\n\ncollate_func = partial(\n    processor_with_lm.feature_extractor,\n    return_tensors=\"pt\", sampling_rate=SAMPLING_RATE,\n    padding=True,\n)\n\ntest_loader = torch.utils.data.DataLoader(\n    test_dataset, batch_size=4, shuffle=False,\n    num_workers=2, collate_fn=collate_func, drop_last=False,\n    pin_memory=True,\n)","metadata":{"execution":{"iopub.status.busy":"2023-10-18T06:22:11.108098Z","iopub.status.idle":"2023-10-18T06:22:11.108454Z","shell.execute_reply.started":"2023-10-18T06:22:11.108290Z","shell.execute_reply":"2023-10-18T06:22:11.108307Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Inference","metadata":{}},{"cell_type":"code","source":"if not torch.cuda.is_available():\n    device = torch.device(\"cpu\")\nelse:\n    device = torch.device(\"cuda\")\nprint(device)","metadata":{"execution":{"iopub.status.busy":"2023-10-18T06:22:11.109638Z","iopub.status.idle":"2023-10-18T06:22:11.110016Z","shell.execute_reply.started":"2023-10-18T06:22:11.109845Z","shell.execute_reply":"2023-10-18T06:22:11.109868Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = model.to(device)\nmodel = model.eval()\nmodel = model.half()","metadata":{"execution":{"iopub.status.busy":"2023-10-18T06:22:11.111637Z","iopub.status.idle":"2023-10-18T06:22:11.112166Z","shell.execute_reply.started":"2023-10-18T06:22:11.111897Z","shell.execute_reply":"2023-10-18T06:22:11.111922Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pred_sentence_list = []\n\nwith torch.no_grad():\n    for batch in tqdm(test_loader):\n        x = batch[\"input_values\"]\n        x = x.to(device, non_blocking=True)\n        with torch.cuda.amp.autocast(True):\n            y = model(x).logits\n        y = y.detach().cpu().numpy()\n        \n        for l in y:  \n            sentence = processor_with_lm.decode(l, beam_width=512).text\n            pred_sentence_list.append(sentence)","metadata":{"execution":{"iopub.status.busy":"2023-10-18T06:22:11.113347Z","iopub.status.idle":"2023-10-18T06:22:11.113657Z","shell.execute_reply.started":"2023-10-18T06:22:11.113510Z","shell.execute_reply":"2023-10-18T06:22:11.113525Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Make Submission","metadata":{}},{"cell_type":"code","source":"bnorm = Normalizer()\n\ndef postprocess(sentence):\n    period_set = set([\".\", \"?\", \"!\", \"।\"])\n    _words = [bnorm(word)['normalized']  for word in sentence.split()]\n    sentence = \" \".join([word for word in _words if word is not None])\n    try:\n        if sentence[-1] not in period_set:\n            sentence+=\"।\"\n    except:\n        # print(sentence)\n        sentence = \"।\"\n    return sentence","metadata":{"execution":{"iopub.status.busy":"2023-10-18T06:22:11.115230Z","iopub.status.idle":"2023-10-18T06:22:11.115558Z","shell.execute_reply.started":"2023-10-18T06:22:11.115394Z","shell.execute_reply":"2023-10-18T06:22:11.115410Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pp_pred_sentence_list = [\n    postprocess(s) for s in tqdm(pred_sentence_list)]","metadata":{"execution":{"iopub.status.busy":"2023-10-18T06:22:11.116511Z","iopub.status.idle":"2023-10-18T06:22:11.116844Z","shell.execute_reply.started":"2023-10-18T06:22:11.116668Z","shell.execute_reply":"2023-10-18T06:22:11.116683Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test[\"sentence\"] = pp_pred_sentence_list\n\ntest.to_csv(\"submission.csv\", index=False)\n\nprint(test.head())","metadata":{"execution":{"iopub.status.busy":"2023-10-18T06:22:11.117727Z","iopub.status.idle":"2023-10-18T06:22:11.118083Z","shell.execute_reply.started":"2023-10-18T06:22:11.117917Z","shell.execute_reply":"2023-10-18T06:22:11.117934Z"},"trusted":true},"execution_count":null,"outputs":[]}]}