{"id":18524068,"url":"https://github.com/atharv-naik/whale-call-classification","last_synced_at":"2026-02-02T05:02:40.401Z","repository":{"id":180423007,"uuid":"600132800","full_name":"atharv-naik/whale-call-classification","owner":"atharv-naik","description":"A CNN model for classifying whale calls","archived":false,"fork":false,"pushed_at":"2024-10-01T16:37:08.000Z","size":2742,"stargazers_count":3,"open_issues_count":4,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-11-13T17:31:59.831Z","etag":null,"topics":["audio-feature-extraction","audio-processing","convolutional-neural-networks","deep-learning","ffmpeg","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/atharv-naik.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-02-10T16:54:18.000Z","updated_at":"2024-10-01T10:04:24.000Z","dependencies_parsed_at":null,"dependency_job_id":"ae2f2387-799a-4617-b2b3-e114695b3cf8","html_url":"https://github.com/atharv-naik/whale-call-classification","commit_stats":null,"previous_names":["atharv-naik/whale-call-classification"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/atharv-naik/whale-call-classification","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atharv-naik%2Fwhale-call-classification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atharv-naik%2Fwhale-call-classification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atharv-naik%2Fwhale-call-classification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atharv-naik%2Fwhale-call-classification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/atharv-naik","download_url":"https://codeload.github.com/atharv-naik/whale-call-classification/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atharv-naik%2Fwhale-call-classification/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29006081,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-02T04:25:24.522Z","status":"ssl_error","status_checked_at":"2026-02-02T04:24:51.069Z","response_time":58,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["audio-feature-extraction","audio-processing","convolutional-neural-networks","deep-learning","ffmpeg","tensorflow"],"created_at":"2024-11-06T17:39:27.477Z","updated_at":"2026-02-02T05:02:40.363Z","avatar_url":"https://github.com/atharv-naik.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Whale Call Classification\n\nThis project aims to classify Blue whale calls into A-calls or not based on a training dataset provided as a part of ISI DataFest Integration 2023. A-Calls are the most commonly heard vocalization of Blue whales and play an important role in their communication and behavior.\n\nThe project uses a Convolutional Neural Network (CNN) to classify the Blue whale calls. The CNN model is trained on a training dataset consisting of ~2600 samples and validated on a ~10% samples. The trained model was then tested on a separate testing dataset consisting of ~1000 samples.\n\n## Installation\n\nClone the repo and cd into it. To install the required packages, run the following command:\n```\npip install -r requirements.txt\n```\nDownload the dataset from the competetion link [here](https://www.kaggle.com/competitions/datafestintegration2023/data) or using the kaggle API, run:\n```\nkaggle competitions download -c datafestintegration2023\n```\nMake sure the dataset is in the same directory as the working directory.\n\n## Usage\n\nFirst preprocess the data. Install ffmpeg which is a dependancy for ```make_aiff.py``` and then preprocess the data. Run the following commands:\n```\nsudo apt install ffmpeg\npython make_aiff.py\npython preprocess.py\n```\n\nTo train the model, run the following command:\n\n```\npython train.py\n```\n\n## Dataset\n\nThe dataset consists of labeled audio files of Blue whale calls in WAV format. The files are categorized as A-call or not based on their spectrogram.\n\n## Model Architecture\n\nThe CNN model consists of 3 convolutional layers, followed by 2 fully connected layers, and an output layer. The model is trained with binary cross-entropy loss and Adam optimizer.\n\n## Results\n\nThe model achieved an accuracy of 97% on the test set.\n\n## Authors\n\n- [@atharv-naik](https://www.github.com/atharv-naik)\n- [@Arg-10](https://www.github.com/Arg-10)\n- [@SomnathRoy123](https://www.github.com/SomnathRoy123)\n\n## License\n\nThis project is licensed under the [MIT](LICENSE) license.\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/Arg-10/Whale-Call-Classification/blob/main/LICENSE)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatharv-naik%2Fwhale-call-classification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fatharv-naik%2Fwhale-call-classification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatharv-naik%2Fwhale-call-classification/lists"}