{"id":16272074,"url":"https://github.com/sshh12/conv-vad","last_synced_at":"2025-03-19T23:31:01.483Z","repository":{"id":70737698,"uuid":"188485209","full_name":"sshh12/Conv-VAD","owner":"sshh12","description":"A packaged convolutional voice activity detector for noisy environments.","archived":false,"fork":false,"pushed_at":"2019-06-15T16:28:24.000Z","size":16,"stargazers_count":14,"open_issues_count":0,"forks_count":2,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-02-28T21:41:37.792Z","etag":null,"topics":["convolutional-neural-networks","keras","melspectrogram","vad","voice-activity-detection"],"latest_commit_sha":null,"homepage":"","language":"Python","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/sshh12.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}},"created_at":"2019-05-24T20:43:16.000Z","updated_at":"2024-05-15T03:01:19.000Z","dependencies_parsed_at":"2023-02-22T22:15:13.754Z","dependency_job_id":null,"html_url":"https://github.com/sshh12/Conv-VAD","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sshh12%2FConv-VAD","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sshh12%2FConv-VAD/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sshh12%2FConv-VAD/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sshh12%2FConv-VAD/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sshh12","download_url":"https://codeload.github.com/sshh12/Conv-VAD/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244031033,"owners_count":20386534,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["convolutional-neural-networks","keras","melspectrogram","vad","voice-activity-detection"],"created_at":"2024-10-10T18:16:00.468Z","updated_at":"2025-03-19T23:31:01.478Z","avatar_url":"https://github.com/sshh12.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Conv VAD\n\n\u003e A packaged convolutional voice activity detector for noisy environments.\n\n## Usage\n\n#### Install\n`pip install https://github.com/sshh12/Conv-VAD/releases/download/v0.1.1/conv-vad-0.1.1.tar.gz`\n\n##### API\n\n```python\nimport conv_vad\n\nvad = conv_vad.VAD()\n\n# Audio frame is numpy array of 1 sec, 16k, single channel audio data.\nscore = vad.score_speech(audio_frame)\n```\n\n##### Demo\n\n```python\nfrom scipy.io import wavfile\nimport numpy as np\nimport conv_vad\n\n# Conv VAD currently only supports single channel audio at a 16k sample rate.\nRATE = 16000\n\n# Create a VAD object and load model\nvad = conv_vad.VAD()\n\n# Load wav as numpy array\naudio = wavfile.read('test.wav')[1].astype(np.uint16)\n\nfor i in range(0, audio.shape[0] - RATE, RATE):\n\n    audio_frame = audio[i:i+RATE]\n\n    # For each audio frame (1 sec) compute the speech score.\n    # 1 = voice, 0 = no voice\n    score = vad.score_speech(audio_frame)\n    print('Time =', i // RATE)\n    print('Speech Score: ', score)\n```\n\n## DIY\n\n#### Creating a dataset\n`python model/label_data.py --wav_path path/to/audio.wav --data_path data`\n\n#### Training\n`python model/train.py --data_path data --epochs 25`\n\n## Related\n\n* [wiseman/py-webrtcvad](https://github.com/wiseman/py-webrtcvad)\n* [belisariops/ConvVAD](https://github.com/belisariops/ConvVAD)\n* [gvashkevich/vad](https://github.com/gvashkevich/vad)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsshh12%2Fconv-vad","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsshh12%2Fconv-vad","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsshh12%2Fconv-vad/lists"}