{"id":29100680,"url":"https://github.com/bagustris/w2v2-vad","last_synced_at":"2025-06-28T18:38:06.856Z","repository":{"id":60163405,"uuid":"464127784","full_name":"bagustris/w2v2-vad","owner":"bagustris","description":"A wrapper for Audeering's wav2vec-based dimensional speech emotion recognition","archived":false,"fork":false,"pushed_at":"2023-08-09T08:33:43.000Z","size":378,"stargazers_count":11,"open_issues_count":1,"forks_count":3,"subscribers_count":3,"default_branch":"master","last_synced_at":"2023-08-09T09:59:31.982Z","etag":null,"topics":["affective-computing","sentiment-analysis","speech-emotion-recognition"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bagustris.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-02-27T12:17:19.000Z","updated_at":"2023-08-08T06:42:27.000Z","dependencies_parsed_at":"2022-09-26T03:00:31.830Z","dependency_job_id":null,"html_url":"https://github.com/bagustris/w2v2-vad","commit_stats":null,"previous_names":[],"tags_count":1,"template":null,"template_full_name":null,"purl":"pkg:github/bagustris/w2v2-vad","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bagustris%2Fw2v2-vad","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bagustris%2Fw2v2-vad/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bagustris%2Fw2v2-vad/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bagustris%2Fw2v2-vad/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bagustris","download_url":"https://codeload.github.com/bagustris/w2v2-vad/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bagustris%2Fw2v2-vad/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262478473,"owners_count":23317690,"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":["affective-computing","sentiment-analysis","speech-emotion-recognition"],"created_at":"2025-06-28T18:38:06.279Z","updated_at":"2025-06-28T18:38:06.847Z","avatar_url":"https://github.com/bagustris.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# w2v2-vad\nA wrapper for Audeering's wav2vector-based dimensional speech emotion recognition (arousal, dominance, and valence).\n\n## Input-output\ninput: any audio file readable by torchaudio at any sample rate (will be resampled to 16000 Hz on the fly)  \noutput:  score of valence, arousal, and dominance in a range [0, 1]  \n\n## Virtual Environment\nI recommend using a virtual environment to run this script. You can use either `venv` or `conda`. I prefer \nto use (Mini) conda now over venv. Here is the example.\n    \n    conda create -n w2v2-vad python=3.8\n    conda activate w2v2-vad\n\n## Installation\n    pip3 install -r requirements.txt\n    \n## Usage\n    python3 predict_vad_w2v2.py input.wav\n\n## Arguments\n```\nPositional: input file at any sample rate\nOptional:  \n-s split, `chunks` or `full`, default is full.  \n-d duration, duration in seconds (if the split is chunks, must be specified)  \n```\n\n## Example\n\n```\nbagus@L140MU:w2v2-vad$ python3 predict_vad_w2v2.py bagus-test_16000.wav \nArousal, dominance, and valence #0: [[0.32293236 0.41639617 0.5942142 ]]\nbagus@L140MU:w2v2-vad$ python3 predict_vad_w2v2.py bagus-test_16000.wav -s chunks -d 2\nArousal, dominance, and valence #0: [[0.3404813  0.42247295 0.35256445]]\nArousal, dominance, and valence #1: [[0.22009875 0.322832   0.51018834]]\nArousal, dominance, and valence #2: [[0.3478799  0.4332775  0.45645887]]\nArousal, dominance, and valence #3: [[0.29967275 0.4038131  0.4949872 ]]\nArousal, dominance, and valence #4: [[0.24804251 0.33543587 0.50990975]]\nArousal, dominance, and valence #5: [[0.38564402 0.43214017 0.37035757]]\n```\n\n## Demo (v1.0)\n[![asciicast](https://asciinema.org/a/1XhSclhNuVsfG6bBCPoQLwvN1.svg)](https://asciinema.org/a/1XhSclhNuVsfG6bBCPoQLwvN1)\n\n## Original repo  \nhttps://github.com/audeering/w2v2-how-to\n\nAll credit goes to Audeering.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbagustris%2Fw2v2-vad","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbagustris%2Fw2v2-vad","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbagustris%2Fw2v2-vad/lists"}