{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":91844,"databundleVersionId":11361821,"sourceType":"competition"},{"sourceId":11747323,"sourceType":"datasetVersion","datasetId":7374555}],"dockerImageVersionId":31012,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"set1=['1139490', '1192948', '1194042', '126247', '1346504', '134933', '135045', '1462711', '1462737', '1564122', '21038', '21116', '21211', '22333', '22973', '22976', '24272', '24292', '24322', '41663', '41778', '41970', '42007', '42087', '42113', '46010', '47067', '476537', '476538', '48124', '50186', '517119', '523060', '528041', '52884', '548639', '555086', '555142', '566513', '64862', '65336', '65344']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-09T10:16:05.034715Z","iopub.execute_input":"2025-05-09T10:16:05.035064Z","iopub.status.idle":"2025-05-09T10:16:05.043188Z","shell.execute_reply.started":"2025-05-09T10:16:05.035037Z","shell.execute_reply":"2025-05-09T10:16:05.041605Z"}},"outputs":[],"execution_count":3},{"cell_type":"code","source":"INPUT_DIR = \"/kaggle/input/birdclef-2025/train_audio\"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-09T10:16:05.595958Z","iopub.execute_input":"2025-05-09T10:16:05.596382Z","iopub.status.idle":"2025-05-09T10:16:05.605599Z","shell.execute_reply.started":"2025-05-09T10:16:05.596345Z","shell.execute_reply":"2025-05-09T10:16:05.603545Z"}},"outputs":[],"execution_count":4},{"cell_type":"code","source":"import os\nall_files=[]\nfor names in set1:\n print(os.path.join(\"/kaggle/input/birdclef-2025/train_audio\",names))\n all_files.append(os.path.join(\"/kaggle/input/birdclef-2025/train_audio\",names))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-09T10:16:06.100778Z","iopub.execute_input":"2025-05-09T10:16:06.101081Z","iopub.status.idle":"2025-05-09T10:16:06.109325Z","shell.execute_reply.started":"2025-05-09T10:16:06.101056Z","shell.execute_reply":"2025-05-09T10:16:06.107645Z"}},"outputs":[{"name":"stdout","text":"/kaggle/input/birdclef-2025/train_audio/1139490\n/kaggle/input/birdclef-2025/train_audio/1192948\n/kaggle/input/birdclef-2025/train_audio/1194042\n/kaggle/input/birdclef-2025/train_audio/126247\n/kaggle/input/birdclef-2025/train_audio/1346504\n/kaggle/input/birdclef-2025/train_audio/134933\n/kaggle/input/birdclef-2025/train_audio/135045\n/kaggle/input/birdclef-2025/train_audio/1462711\n/kaggle/input/birdclef-2025/train_audio/1462737\n/kaggle/input/birdclef-2025/train_audio/1564122\n/kaggle/input/birdclef-2025/train_audio/21038\n/kaggle/input/birdclef-2025/train_audio/21116\n/kaggle/input/birdclef-2025/train_audio/21211\n/kaggle/input/birdclef-2025/train_audio/22333\n/kaggle/input/birdclef-2025/train_audio/22973\n/kaggle/input/birdclef-2025/train_audio/22976\n/kaggle/input/birdclef-2025/train_audio/24272\n/kaggle/input/birdclef-2025/train_audio/24292\n/kaggle/input/birdclef-2025/train_audio/24322\n/kaggle/input/birdclef-2025/train_audio/41663\n/kaggle/input/birdclef-2025/train_audio/41778\n/kaggle/input/birdclef-2025/train_audio/41970\n/kaggle/input/birdclef-2025/train_audio/42007\n/kaggle/input/birdclef-2025/train_audio/42087\n/kaggle/input/birdclef-2025/train_audio/42113\n/kaggle/input/birdclef-2025/train_audio/46010\n/kaggle/input/birdclef-2025/train_audio/47067\n/kaggle/input/birdclef-2025/train_audio/476537\n/kaggle/input/birdclef-2025/train_audio/476538\n/kaggle/input/birdclef-2025/train_audio/48124\n/kaggle/input/birdclef-2025/train_audio/50186\n/kaggle/input/birdclef-2025/train_audio/517119\n/kaggle/input/birdclef-2025/train_audio/523060\n/kaggle/input/birdclef-2025/train_audio/528041\n/kaggle/input/birdclef-2025/train_audio/52884\n/kaggle/input/birdclef-2025/train_audio/548639\n/kaggle/input/birdclef-2025/train_audio/555086\n/kaggle/input/birdclef-2025/train_audio/555142\n/kaggle/input/birdclef-2025/train_audio/566513\n/kaggle/input/birdclef-2025/train_audio/64862\n/kaggle/input/birdclef-2025/train_audio/65336\n/kaggle/input/birdclef-2025/train_audio/65344\n","output_type":"stream"}],"execution_count":5},{"cell_type":"code","source":"from kaggle_secrets import UserSecretsClient\nuser_secrets = UserSecretsClient()\nsecret_value_0 = user_secrets.get_secret(\"HF_TOKEN\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-09T10:16:07.035308Z","iopub.execute_input":"2025-05-09T10:16:07.035644Z","iopub.status.idle":"2025-05-09T10:16:07.254433Z","shell.execute_reply.started":"2025-05-09T10:16:07.035617Z","shell.execute_reply":"2025-05-09T10:16:07.253429Z"}},"outputs":[],"execution_count":6},{"cell_type":"code","source":"import os\nfrom kaggle_secrets import UserSecretsClient\n\n# Load Hugging Face token\nuser_secrets = UserSecretsClient()\nos.environ[\"HF_TOKEN\"] = user_secrets.get_secret(\"HF_TOKEN\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-09T10:16:10.004492Z","iopub.execute_input":"2025-05-09T10:16:10.004801Z","iopub.status.idle":"2025-05-09T10:16:10.179158Z","shell.execute_reply.started":"2025-05-09T10:16:10.004778Z","shell.execute_reply":"2025-05-09T10:16:10.178331Z"}},"outputs":[],"execution_count":7},{"cell_type":"code","source":"!pip install pyannote.audio librosa soundfile numpy huggingface_hub tqdm","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-09T10:16:10.541756Z","iopub.execute_input":"2025-05-09T10:16:10.542239Z","iopub.status.idle":"2025-05-09T10:18:07.754227Z","shell.execute_reply.started":"2025-05-09T10:16:10.542207Z","shell.execute_reply":"2025-05-09T10:18:07.752832Z"}},"outputs":[{"name":"stdout","text":"Collecting pyannote.audio\n Downloading pyannote.audio-3.3.2-py2.py3-none-any.whl.metadata (11 kB)\nRequirement already satisfied: librosa in /usr/local/lib/python3.11/dist-packages (0.10.2.post1)\nRequirement already satisfied: soundfile in /usr/local/lib/python3.11/dist-packages (0.13.1)\nRequirement already satisfied: numpy in /usr/local/lib/python3.11/dist-packages (1.26.4)\nRequirement already satisfied: huggingface_hub in /usr/local/lib/python3.11/dist-packages (0.30.2)\nRequirement already satisfied: tqdm in /usr/local/lib/python3.11/dist-packages (4.67.1)\nCollecting asteroid-filterbanks>=0.4 (from pyannote.audio)\n Downloading asteroid_filterbanks-0.4.0-py3-none-any.whl.metadata (3.3 kB)\nRequirement already satisfied: einops>=0.6.0 in /usr/local/lib/python3.11/dist-packages (from pyannote.audio) (0.8.1)\nCollecting lightning>=2.0.1 (from pyannote.audio)\n Downloading lightning-2.5.1.post0-py3-none-any.whl.metadata (39 kB)\nRequirement already satisfied: omegaconf<3.0,>=2.1 in /usr/local/lib/python3.11/dist-packages (from pyannote.audio) (2.3.0)\nCollecting pyannote.core>=5.0.0 (from pyannote.audio)\n Downloading pyannote.core-5.0.0-py3-none-any.whl.metadata (1.4 kB)\nCollecting pyannote.database>=5.0.1 (from pyannote.audio)\n Downloading pyannote.database-5.1.3-py3-none-any.whl.metadata (1.1 kB)\nCollecting pyannote.metrics>=3.2 (from pyannote.audio)\n Downloading pyannote.metrics-3.2.1-py3-none-any.whl.metadata (1.3 kB)\nCollecting pyannote.pipeline>=3.0.1 (from pyannote.audio)\n Downloading pyannote.pipeline-3.0.1-py3-none-any.whl.metadata (897 bytes)\nCollecting pytorch-metric-learning>=2.1.0 (from pyannote.audio)\n Downloading pytorch_metric_learning-2.8.1-py3-none-any.whl.metadata (18 kB)\nRequirement already satisfied: rich>=12.0.0 in /usr/local/lib/python3.11/dist-packages (from pyannote.audio) (14.0.0)\nRequirement already satisfied: semver>=3.0.0 in /usr/local/lib/python3.11/dist-packages (from pyannote.audio) (3.0.4)\nCollecting speechbrain>=1.0.0 (from pyannote.audio)\n Downloading speechbrain-1.0.3-py3-none-any.whl.metadata (24 kB)\nCollecting tensorboardX>=2.6 (from pyannote.audio)\n Downloading tensorboardX-2.6.2.2-py2.py3-none-any.whl.metadata (5.8 kB)\nRequirement already satisfied: torch>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from pyannote.audio) (2.5.1+cu124)\nCollecting torch-audiomentations>=0.11.0 (from pyannote.audio)\n Downloading torch_audiomentations-0.12.0-py3-none-any.whl.metadata (15 kB)\nRequirement already satisfied: torchaudio>=2.2.0 in /usr/local/lib/python3.11/dist-packages (from pyannote.audio) (2.5.1+cu124)\nRequirement already satisfied: torchmetrics>=0.11.0 in /usr/local/lib/python3.11/dist-packages (from pyannote.audio) (1.7.1)\nRequirement already satisfied: audioread>=2.1.9 in /usr/local/lib/python3.11/dist-packages (from librosa) (3.0.1)\nRequirement already satisfied: scipy>=1.2.0 in /usr/local/lib/python3.11/dist-packages (from librosa) (1.15.2)\nRequirement already satisfied: scikit-learn>=0.20.0 in /usr/local/lib/python3.11/dist-packages (from librosa) (1.2.2)\nRequirement already satisfied: joblib>=0.14 in /usr/local/lib/python3.11/dist-packages (from librosa) (1.4.2)\nRequirement already satisfied: decorator>=4.3.0 in /usr/local/lib/python3.11/dist-packages (from librosa) (4.4.2)\nRequirement already satisfied: numba>=0.51.0 in /usr/local/lib/python3.11/dist-packages (from librosa) (0.60.0)\nRequirement already satisfied: pooch>=1.1 in /usr/local/lib/python3.11/dist-packages (from librosa) (1.8.2)\nRequirement already satisfied: soxr>=0.3.2 in /usr/local/lib/python3.11/dist-packages (from librosa) (0.5.0.post1)\nRequirement already satisfied: typing-extensions>=4.1.1 in /usr/local/lib/python3.11/dist-packages (from librosa) (4.13.1)\nRequirement already satisfied: lazy-loader>=0.1 in /usr/local/lib/python3.11/dist-packages (from librosa) (0.4)\nRequirement already satisfied: msgpack>=1.0 in /usr/local/lib/python3.11/dist-packages (from librosa) (1.1.0)\nRequirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.11/dist-packages (from soundfile) (1.17.1)\nRequirement already satisfied: mkl_fft in /usr/local/lib/python3.11/dist-packages (from numpy) (1.3.8)\nRequirement already satisfied: mkl_random in /usr/local/lib/python3.11/dist-packages (from numpy) (1.2.4)\nRequirement already satisfied: mkl_umath in /usr/local/lib/python3.11/dist-packages (from numpy) (0.1.1)\nRequirement already satisfied: mkl in /usr/local/lib/python3.11/dist-packages (from numpy) (2025.1.0)\nRequirement already satisfied: tbb4py in /usr/local/lib/python3.11/dist-packages (from numpy) (2022.1.0)\nRequirement already satisfied: mkl-service in /usr/local/lib/python3.11/dist-packages (from numpy) (2.4.1)\nRequirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (3.18.0)\nRequirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (2025.3.2)\nRequirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (24.2)\nRequirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (6.0.2)\nRequirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (2.32.3)\nRequirement already satisfied: pycparser in /usr/local/lib/python3.11/dist-packages (from cffi>=1.0->soundfile) (2.22)\nRequirement already satisfied: lightning-utilities<2.0,>=0.10.0 in /usr/local/lib/python3.11/dist-packages (from lightning>=2.0.1->pyannote.audio) (0.14.3)\nRequirement already satisfied: pytorch-lightning in /usr/local/lib/python3.11/dist-packages (from lightning>=2.0.1->pyannote.audio) (2.5.1)\nRequirement already satisfied: llvmlite<0.44,>=0.43.0dev0 in /usr/local/lib/python3.11/dist-packages (from numba>=0.51.0->librosa) (0.43.0)\nRequirement already satisfied: antlr4-python3-runtime==4.9.* in /usr/local/lib/python3.11/dist-packages (from omegaconf<3.0,>=2.1->pyannote.audio) (4.9.3)\nRequirement already satisfied: platformdirs>=2.5.0 in /usr/local/lib/python3.11/dist-packages (from pooch>=1.1->librosa) (4.3.7)\nRequirement already satisfied: sortedcontainers>=2.0.4 in /usr/local/lib/python3.11/dist-packages (from pyannote.core>=5.0.0->pyannote.audio) (2.4.0)\nRequirement already satisfied: pandas>=0.19 in /usr/local/lib/python3.11/dist-packages (from pyannote.database>=5.0.1->pyannote.audio) (2.2.3)\nRequirement already satisfied: typer>=0.12.1 in /usr/local/lib/python3.11/dist-packages (from pyannote.database>=5.0.1->pyannote.audio) (0.15.1)\nCollecting docopt>=0.6.2 (from pyannote.metrics>=3.2->pyannote.audio)\n Downloading docopt-0.6.2.tar.gz (25 kB)\n Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\nRequirement already satisfied: tabulate>=0.7.7 in /usr/local/lib/python3.11/dist-packages (from pyannote.metrics>=3.2->pyannote.audio) (0.9.0)\nRequirement already satisfied: matplotlib>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from pyannote.metrics>=3.2->pyannote.audio) (3.7.5)\nRequirement already satisfied: sympy>=1.1 in /usr/local/lib/python3.11/dist-packages (from pyannote.metrics>=3.2->pyannote.audio) (1.13.1)\nRequirement already satisfied: optuna>=3.1 in /usr/local/lib/python3.11/dist-packages (from pyannote.pipeline>=3.0.1->pyannote.audio) (4.2.1)\nRequirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface_hub) (3.4.1)\nRequirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface_hub) (3.10)\nRequirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface_hub) (2.3.0)\nRequirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface_hub) (2025.1.31)\nRequirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.11/dist-packages (from rich>=12.0.0->pyannote.audio) (3.0.0)\nRequirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.11/dist-packages (from rich>=12.0.0->pyannote.audio) (2.19.1)\nRequirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn>=0.20.0->librosa) (3.6.0)\nCollecting hyperpyyaml (from speechbrain>=1.0.0->pyannote.audio)\n Downloading HyperPyYAML-1.2.2-py3-none-any.whl.metadata (7.6 kB)\nRequirement already satisfied: sentencepiece in /usr/local/lib/python3.11/dist-packages (from speechbrain>=1.0.0->pyannote.audio) (0.2.0)\nRequirement already satisfied: protobuf>=3.20 in /usr/local/lib/python3.11/dist-packages (from tensorboardX>=2.6->pyannote.audio) (3.20.3)\nRequirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->pyannote.audio) (3.4.2)\nRequirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->pyannote.audio) (3.1.6)\nRequirement already satisfied: nvidia-cuda-nvrtc-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->pyannote.audio) (12.4.127)\nRequirement already satisfied: nvidia-cuda-runtime-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->pyannote.audio) (12.4.127)\nRequirement already satisfied: nvidia-cuda-cupti-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->pyannote.audio) (12.4.127)\nCollecting nvidia-cudnn-cu12==9.1.0.70 (from torch>=2.0.0->pyannote.audio)\n Downloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\nCollecting nvidia-cublas-cu12==12.4.5.8 (from torch>=2.0.0->pyannote.audio)\n Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\nCollecting nvidia-cufft-cu12==11.2.1.3 (from torch>=2.0.0->pyannote.audio)\n Downloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\nCollecting nvidia-curand-cu12==10.3.5.147 (from torch>=2.0.0->pyannote.audio)\n Downloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\nCollecting nvidia-cusolver-cu12==11.6.1.9 (from torch>=2.0.0->pyannote.audio)\n Downloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\nCollecting nvidia-cusparse-cu12==12.3.1.170 (from torch>=2.0.0->pyannote.audio)\n Downloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\nRequirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->pyannote.audio) (2.21.5)\nRequirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->pyannote.audio) (12.4.127)\nCollecting nvidia-nvjitlink-cu12==12.4.127 (from torch>=2.0.0->pyannote.audio)\n Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\nRequirement already satisfied: triton==3.1.0 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->pyannote.audio) (3.1.0)\nRequirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy>=1.1->pyannote.metrics>=3.2->pyannote.audio) (1.3.0)\nCollecting julius<0.3,>=0.2.3 (from torch-audiomentations>=0.11.0->pyannote.audio)\n Downloading julius-0.2.7.tar.gz (59 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m59.6/59.6 kB\u001b[0m \u001b[31m2.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\nCollecting torch-pitch-shift>=1.2.2 (from torch-audiomentations>=0.11.0->pyannote.audio)\n Downloading torch_pitch_shift-1.2.5-py3-none-any.whl.metadata (2.5 kB)\nRequirement already satisfied: intel-openmp<2026,>=2024 in /usr/local/lib/python3.11/dist-packages (from mkl->numpy) (2024.2.0)\nRequirement already satisfied: tbb==2022.* in /usr/local/lib/python3.11/dist-packages (from mkl->numpy) (2022.1.0)\nRequirement already satisfied: tcmlib==1.* in /usr/local/lib/python3.11/dist-packages (from tbb==2022.*->mkl->numpy) (1.2.0)\nRequirement already satisfied: intel-cmplr-lib-rt in /usr/local/lib/python3.11/dist-packages (from mkl_umath->numpy) (2024.2.0)\nRequirement already satisfied: aiohttp!=4.0.0a0,!=4.0.0a1 in /usr/local/lib/python3.11/dist-packages (from fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio) (3.11.16)\nRequirement already satisfied: intel-cmplr-lib-ur==2024.2.0 in /usr/local/lib/python3.11/dist-packages (from intel-openmp<2026,>=2024->mkl->numpy) (2024.2.0)\nRequirement already satisfied: setuptools in /usr/local/lib/python3.11/dist-packages (from lightning-utilities<2.0,>=0.10.0->lightning>=2.0.1->pyannote.audio) (75.1.0)\nRequirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.11/dist-packages (from markdown-it-py>=2.2.0->rich>=12.0.0->pyannote.audio) (0.1.2)\nRequirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=2.0.0->pyannote.metrics>=3.2->pyannote.audio) (1.3.1)\nRequirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=2.0.0->pyannote.metrics>=3.2->pyannote.audio) (0.12.1)\nRequirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=2.0.0->pyannote.metrics>=3.2->pyannote.audio) (4.56.0)\nRequirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=2.0.0->pyannote.metrics>=3.2->pyannote.audio) (1.4.8)\nRequirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=2.0.0->pyannote.metrics>=3.2->pyannote.audio) (11.1.0)\nRequirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=2.0.0->pyannote.metrics>=3.2->pyannote.audio) (3.2.1)\nRequirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=2.0.0->pyannote.metrics>=3.2->pyannote.audio) (2.9.0.post0)\nRequirement already satisfied: alembic>=1.5.0 in /usr/local/lib/python3.11/dist-packages (from optuna>=3.1->pyannote.pipeline>=3.0.1->pyannote.audio) (1.15.2)\nRequirement already satisfied: colorlog in /usr/local/lib/python3.11/dist-packages (from optuna>=3.1->pyannote.pipeline>=3.0.1->pyannote.audio) (6.9.0)\nRequirement already satisfied: sqlalchemy>=1.4.2 in /usr/local/lib/python3.11/dist-packages (from optuna>=3.1->pyannote.pipeline>=3.0.1->pyannote.audio) (2.0.38)\nRequirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas>=0.19->pyannote.database>=5.0.1->pyannote.audio) (2025.2)\nRequirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas>=0.19->pyannote.database>=5.0.1->pyannote.audio) (2025.2)\nCollecting primePy>=1.3 (from torch-pitch-shift>=1.2.2->torch-audiomentations>=0.11.0->pyannote.audio)\n Downloading primePy-1.3-py3-none-any.whl.metadata (4.8 kB)\nRequirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.11/dist-packages (from typer>=0.12.1->pyannote.database>=5.0.1->pyannote.audio) (8.1.8)\nRequirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.11/dist-packages (from typer>=0.12.1->pyannote.database>=5.0.1->pyannote.audio) (1.5.4)\nCollecting ruamel.yaml>=0.17.28 (from hyperpyyaml->speechbrain>=1.0.0->pyannote.audio)\n Downloading ruamel.yaml-0.18.10-py3-none-any.whl.metadata (23 kB)\nRequirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from jinja2->torch>=2.0.0->pyannote.audio) (3.0.2)\nRequirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio) (2.6.1)\nRequirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio) (1.3.2)\nRequirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio) (25.3.0)\nRequirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio) (1.5.0)\nRequirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio) (6.2.0)\nRequirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio) (0.3.1)\nRequirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning>=2.0.1->pyannote.audio) (1.19.0)\nRequirement already satisfied: Mako in /usr/local/lib/python3.11/dist-packages (from alembic>=1.5.0->optuna>=3.1->pyannote.pipeline>=3.0.1->pyannote.audio) (1.3.9)\nRequirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.7->matplotlib>=2.0.0->pyannote.metrics>=3.2->pyannote.audio) (1.17.0)\nCollecting ruamel.yaml.clib>=0.2.7 (from ruamel.yaml>=0.17.28->hyperpyyaml->speechbrain>=1.0.0->pyannote.audio)\n Downloading ruamel.yaml.clib-0.2.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (2.7 kB)\nRequirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.11/dist-packages (from sqlalchemy>=1.4.2->optuna>=3.1->pyannote.pipeline>=3.0.1->pyannote.audio) (3.1.1)\nDownloading pyannote.audio-3.3.2-py2.py3-none-any.whl (898 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m898.7/898.7 kB\u001b[0m \u001b[31m24.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m\n\u001b[?25hDownloading asteroid_filterbanks-0.4.0-py3-none-any.whl (29 kB)\nDownloading lightning-2.5.1.post0-py3-none-any.whl (819 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m819.0/819.0 kB\u001b[0m \u001b[31m20.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m\n\u001b[?25hDownloading pyannote.core-5.0.0-py3-none-any.whl (58 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.5/58.5 kB\u001b[0m \u001b[31m2.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading pyannote.database-5.1.3-py3-none-any.whl (48 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m48.1/48.1 kB\u001b[0m \u001b[31m1.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading pyannote.metrics-3.2.1-py3-none-any.whl (51 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m51.4/51.4 kB\u001b[0m \u001b[31m2.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading pyannote.pipeline-3.0.1-py3-none-any.whl (31 kB)\nDownloading pytorch_metric_learning-2.8.1-py3-none-any.whl (125 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m125.9/125.9 kB\u001b[0m \u001b[31m4.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading speechbrain-1.0.3-py3-none-any.whl (864 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m864.1/864.1 kB\u001b[0m \u001b[31m13.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n\u001b[?25hDownloading tensorboardX-2.6.2.2-py2.py3-none-any.whl (101 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m101.7/101.7 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl (363.4 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m363.4/363.4 MB\u001b[0m \u001b[31m4.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m0:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl (664.8 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m664.8/664.8 MB\u001b[0m \u001b[31m2.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0mm\n\u001b[?25hDownloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl (211.5 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m211.5/211.5 MB\u001b[0m \u001b[31m6.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m0:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl (56.3 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.3/56.3 MB\u001b[0m \u001b[31m25.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m0:01\u001b[0mm\n\u001b[?25hDownloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl (127.9 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m127.9/127.9 MB\u001b[0m \u001b[31m2.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m0:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl (207.5 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.5/207.5 MB\u001b[0m \u001b[31m3.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m0:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m61.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading torch_audiomentations-0.12.0-py3-none-any.whl (48 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m48.5/48.5 kB\u001b[0m \u001b[31m1.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading torch_pitch_shift-1.2.5-py3-none-any.whl (5.0 kB)\nDownloading HyperPyYAML-1.2.2-py3-none-any.whl (16 kB)\nDownloading primePy-1.3-py3-none-any.whl (4.0 kB)\nDownloading ruamel.yaml-0.18.10-py3-none-any.whl (117 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m117.7/117.7 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0meta \u001b[36m0:00:01\u001b[0m\n\u001b[?25hDownloading ruamel.yaml.clib-0.2.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (739 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m739.1/739.1 kB\u001b[0m \u001b[31m20.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m\n\u001b[?25hBuilding wheels for collected packages: docopt, julius\n Building wheel for docopt (setup.py) ... \u001b[?25l\u001b[?25hdone\n Created wheel for docopt: filename=docopt-0.6.2-py2.py3-none-any.whl size=13706 sha256=2d47419794fa87f04436166ffbb71624c0f2fc9bdc2f2da97872c6e003065f89\n Stored in directory: /root/.cache/pip/wheels/1a/b0/8c/4b75c4116c31f83c8f9f047231251e13cc74481cca4a78a9ce\n Building wheel for julius (setup.py) ... \u001b[?25l\u001b[?25hdone\n Created wheel for julius: filename=julius-0.2.7-py3-none-any.whl size=21869 sha256=35be0e5cb0b5377430a24fd3fe0f3bf676e88888c5ca79c770019bcd94cc5040\n Stored in directory: /root/.cache/pip/wheels/16/15/d4/edd724cefe78050a6ba3344b8b0c6672db829a799dbb9f81ff\nSuccessfully built docopt julius\nInstalling collected packages: primePy, docopt, ruamel.yaml.clib, nvidia-nvjitlink-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cublas-cu12, ruamel.yaml, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12, hyperpyyaml, julius, torch-pitch-shift, torch-audiomentations, pyannote.core, pyannote.database, tensorboardX, speechbrain, pytorch-metric-learning, pyannote.pipeline, pyannote.metrics, lightning, asteroid-filterbanks, pyannote.audio\n Attempting uninstall: nvidia-nvjitlink-cu12\n Found existing installation: nvidia-nvjitlink-cu12 12.8.93\n Uninstalling nvidia-nvjitlink-cu12-12.8.93:\n Successfully uninstalled nvidia-nvjitlink-cu12-12.8.93\n Attempting uninstall: nvidia-curand-cu12\n Found existing installation: nvidia-curand-cu12 10.3.9.90\n Uninstalling nvidia-curand-cu12-10.3.9.90:\n Successfully uninstalled nvidia-curand-cu12-10.3.9.90\n Attempting uninstall: nvidia-cufft-cu12\n Found existing installation: nvidia-cufft-cu12 11.3.3.83\n Uninstalling nvidia-cufft-cu12-11.3.3.83:\n Successfully uninstalled nvidia-cufft-cu12-11.3.3.83\n Attempting uninstall: nvidia-cublas-cu12\n Found existing installation: nvidia-cublas-cu12 12.8.4.1\n Uninstalling nvidia-cublas-cu12-12.8.4.1:\n Successfully uninstalled nvidia-cublas-cu12-12.8.4.1\n Attempting uninstall: nvidia-cusparse-cu12\n Found existing installation: nvidia-cusparse-cu12 12.5.8.93\n Uninstalling nvidia-cusparse-cu12-12.5.8.93:\n Successfully uninstalled nvidia-cusparse-cu12-12.5.8.93\n Attempting uninstall: nvidia-cudnn-cu12\n Found existing installation: nvidia-cudnn-cu12 9.3.0.75\n Uninstalling nvidia-cudnn-cu12-9.3.0.75:\n Successfully uninstalled nvidia-cudnn-cu12-9.3.0.75\n Attempting uninstall: nvidia-cusolver-cu12\n Found existing installation: nvidia-cusolver-cu12 11.7.3.90\n Uninstalling nvidia-cusolver-cu12-11.7.3.90:\n Successfully uninstalled nvidia-cusolver-cu12-11.7.3.90\n\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\npylibcugraph-cu12 24.12.0 requires pylibraft-cu12==24.12.*, but you have pylibraft-cu12 25.2.0 which is incompatible.\npylibcugraph-cu12 24.12.0 requires rmm-cu12==24.12.*, but you have rmm-cu12 25.2.0 which is incompatible.\u001b[0m\u001b[31m\n\u001b[0mSuccessfully installed asteroid-filterbanks-0.4.0 docopt-0.6.2 hyperpyyaml-1.2.2 julius-0.2.7 lightning-2.5.1.post0 nvidia-cublas-cu12-12.4.5.8 nvidia-cudnn-cu12-9.1.0.70 nvidia-cufft-cu12-11.2.1.3 nvidia-curand-cu12-10.3.5.147 nvidia-cusolver-cu12-11.6.1.9 nvidia-cusparse-cu12-12.3.1.170 nvidia-nvjitlink-cu12-12.4.127 primePy-1.3 pyannote.audio-3.3.2 pyannote.core-5.0.0 pyannote.database-5.1.3 pyannote.metrics-3.2.1 pyannote.pipeline-3.0.1 pytorch-metric-learning-2.8.1 ruamel.yaml-0.18.10 ruamel.yaml.clib-0.2.12 speechbrain-1.0.3 tensorboardX-2.6.2.2 torch-audiomentations-0.12.0 torch-pitch-shift-1.2.5\n","output_type":"stream"}],"execution_count":8},{"cell_type":"code","source":"import os\nimport numpy as np\nimport librosa\nimport soundfile as sf\nfrom pyannote.audio import Pipeline\nfrom tqdm import tqdm\n\n# Initialize the PyAnnote VAD pipeline\nvad_pipeline = Pipeline.from_pretrained(\"pyannote/voice-activity-detection\")\n\ndef clean_audio(input_path, output_path):\n # Load and resample\n waveform, sr = librosa.load(input_path, sr=16000, mono=True)\n duration = len(waveform) / sr\n\n # Detect speech using file path\n try:\n vad_output = vad_pipeline(input_path)\n speech_segments = list(vad_output.get_timeline().support())\n except Exception as e:\n print(f\"VAD failed on {input_path}: {e}\")\n speech_segments = []\n\n # If no speech, save original audio\n if not speech_segments:\n os.makedirs(os.path.dirname(output_path), exist_ok=True)\n sf.write(output_path, waveform, sr)\n return\n\n # Extract non-speech segments\n non_speech_segments = []\n prev_end = 0.0\n for seg in sorted(speech_segments, key=lambda x: x.start):\n if seg.start > prev_end:\n non_speech_segments.append((prev_end, seg.start))\n prev_end = max(prev_end, seg.end)\n if prev_end < duration:\n non_speech_segments.append((prev_end, duration))\n\n # Concatenate and trim\n cleaned_waveform = []\n for start, end in non_speech_segments:\n start_sample = int(start * sr)\n end_sample = int(end * sr)\n cleaned_waveform.append(waveform[start_sample:end_sample])\n \n if len(cleaned_waveform) == 0:\n cleaned_waveform = np.zeros(0)\n else:\n cleaned_waveform = np.concatenate(cleaned_waveform)\n trim_samples = 3 * sr\n if len(cleaned_waveform) > trim_samples:\n cleaned_waveform = cleaned_waveform[:-trim_samples]\n else:\n cleaned_waveform = np.zeros(0)\n\n # Save only if non-empty\n os.makedirs(os.path.dirname(output_path), exist_ok=True)\n if len(cleaned_waveform) > 0:\n sf.write(output_path, cleaned_waveform, sr)\n else:\n print(f\"Skipping empty file: {output_path}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-09T10:18:07.756222Z","iopub.execute_input":"2025-05-09T10:18:07.756736Z","iopub.status.idle":"2025-05-09T10:18:35.974977Z","shell.execute_reply.started":"2025-05-09T10:18:07.756693Z","shell.execute_reply":"2025-05-09T10:18:35.974015Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"config.yaml: 0%| | 0.00/277 [00:00