{"id":23985543,"url":"https://github.com/codename0og/rvc_onnx_infer","last_synced_at":"2026-03-11T01:32:11.570Z","repository":{"id":211529860,"uuid":"729396616","full_name":"codename0og/RVC_Onnx_Infer","owner":"codename0og","description":"RVC Onnx Infer- Upgraded and simplified-ish","archived":false,"fork":false,"pushed_at":"2024-05-09T17:02:33.000Z","size":73,"stargazers_count":21,"open_issues_count":1,"forks_count":1,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-08-11T21:34:44.379Z","etag":null,"topics":[],"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/codename0og.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":"2023-12-09T05:13:51.000Z","updated_at":"2025-06-03T07:53:41.000Z","dependencies_parsed_at":"2024-03-18T20:17:32.210Z","dependency_job_id":"e599ee0d-4b3e-4f47-aa1e-e71b7eea6d6b","html_url":"https://github.com/codename0og/RVC_Onnx_Infer","commit_stats":null,"previous_names":["codename0og/rvc_onnx_infer"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/codename0og/RVC_Onnx_Infer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codename0og%2FRVC_Onnx_Infer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codename0og%2FRVC_Onnx_Infer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codename0og%2FRVC_Onnx_Infer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codename0og%2FRVC_Onnx_Infer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/codename0og","download_url":"https://codeload.github.com/codename0og/RVC_Onnx_Infer/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codename0og%2FRVC_Onnx_Infer/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30366051,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-10T21:41:54.280Z","status":"ssl_error","status_checked_at":"2026-03-10T21:40:59.357Z","response_time":106,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 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":[],"created_at":"2025-01-07T14:16:01.017Z","updated_at":"2026-03-11T01:32:11.529Z","avatar_url":"https://github.com/codename0og.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Codename;0's improved RVC Onnx models Inference.\u003cbr /\u003e\n\n## THE PROJECT IS CURRENTLY PAUSED - NOT ABANDONED.\nCurrently, the basics work; you can infer just fine however there's a length limit ( despite the internal slicing ) of around 50 seconds - at least on my machine.\u003cbr /\u003eI have to find a better and more efficient segmentation mechanism, til then yea.\n\n## Ready to be used with RVC V2 onnx models. ( CPU, Cuda and DML support )\u003cbr /\u003e\n### Todo:\n- Adding index/faiss support\n- Automating stuff / making i/o handling easier.\n- Adding rmvpe f0 method\n- Better automation and easier input/output managment + stuff picker.\n- Possibly even a gui or web-ui ~ one day huh.\n- Quite possibly a tflite model exporting for future Mobile-RVC-infer-port-project ( ***Not 100% sure yet, concept stage.*** )\u003cbr /\u003e\n# Usage guide:\n\n### 1. First, prior to any inferencing, you gotta obtain the: '**vec-768-layer-12.onnx**' file from:\u003cbr /\u003e\n**https://huggingface.co/NaruseMioShirakana/MoeSS-SUBModel/tree/main**\u003cbr /\u003e\n\nPlace it here: RVC_Onnx_Infer/assets/vec\n\u003e reference: '**RVC_Onnx_Infer/assets/vec/vec-768-layer-12.onnx**'\n\n⠀\u003cbr /\u003e\n### 2. Your .onnx models land into '**onnx_models**' folder\n( You set which one to use in the 30th line of '**RVC_Onnx_Infer.py**' script )\n\u003e model_path = os.path.join(\"onnx_models\", \"**Your_Model.onnx**\")  # Your .ONNX model\n\n⠀\u003cbr /\u003e\n### 3. Your vocals for inference / acapella .wav goes into 'input' folder.\n( Script will pick only the first found .wav in there, so, always have just 1 in there to avoid issues. )\n\n⠀\u003cbr /\u003e\n### 4. Your inference outputs will appear in the '**outpit**' folder.\n( One at a time. Any consecutive inferences will overwrite the previous file so, copy / move it somewhere else.\n\n⠀\u003cbr /\u003e\n### 5. To switch the device to Cuda or DML, change \"**cpu**\" to any of the mentioned.\u003cbr /\u003e\nThe 27th line of '**RVC_Onnx_Infer.py**' script;\n\u003e device = \"**cpu**\"  # options: **dml**, **cuda**, **cpu**\n\n⠀\u003cbr /\u003e\n### 6. To change hop_size, replace the '64' value with any desired.\u003cbr /\u003e\nThe 22nd line of '**RVC_Onnx_Infer.py**' script;\n\u003e hop_size = 64 # hop size for inference. ( Currently, applies only to dio F0 )\u003cbr /\u003e\n\u003e Try: 32, 64, 128, 256, 512  or custom of your choice.\n\n⠀\u003cbr /\u003e\n⠀\u003cbr /\u003e\n⠀\u003cbr /\u003e\n# | v0.2a | 10.12.2023 - CHANGELOG: \u003cbr /\u003e\n### Changes:\n- **Inference max length limit off** - No more '50 seconds max' per infer / file length.\u003cbr /\u003e\n( Now it's internally slicing, inferencing the segments 1 by 1 to avoid memory issues and merging it all into 1 final output. )  \n- **DML x CPU is set as default** for the main device.\u003cbr /\u003e\n- PM F0 Pitch estimation: Yea, I sorta fixed it but it's not perfect ( Doesn't support custom hop length too ) - Dio is better.\n\u003e That is, until a workaround for pitch offset / hop length related(?) is found.\n- Cosmetics changes - Made the console a lil bit more fancy lol + logging of segmenting process and so on.\n⠀\u003cbr /\u003e\n⠀\u003cbr /\u003e\n⠀\u003cbr /\u003e\n# INITIAL RELEASE: v0.1a\u003cbr /\u003e\n### Notes:\n- Project is in an **early alpha-dev / test / debug state.**\n- Currently only Dio F0 Pitch estimation until I figure out the rest.\n- It is supporting **RVC V2 onnx models only.**\u003cbr /\u003e\n(V1 models do not work unless you get 256-layer-9 vec onnx and modify the code appropriately.)\n⠀\u003cbr /\u003e\n- **CPU is set by default** as the main device for the sake of compatibility, need more testing.\u003cbr /\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodename0og%2Frvc_onnx_infer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcodename0og%2Frvc_onnx_infer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodename0og%2Frvc_onnx_infer/lists"}