{"id":26488050,"url":"https://github.com/mddct/transformer-vocos","last_synced_at":"2026-01-04T21:05:10.785Z","repository":{"id":282259469,"uuid":"947799030","full_name":"Mddct/transformer-vocos","owner":"Mddct","description":null,"archived":false,"fork":false,"pushed_at":"2025-03-13T15:37:02.000Z","size":14,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-13T16:35:16.379Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"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/Mddct.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-03-13T09:13:43.000Z","updated_at":"2025-03-13T09:18:10.000Z","dependencies_parsed_at":"2025-03-13T19:15:57.643Z","dependency_job_id":null,"html_url":"https://github.com/Mddct/transformer-vocos","commit_stats":null,"previous_names":["mddct/transformer-vocos"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mddct%2Ftransformer-vocos","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mddct%2Ftransformer-vocos/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mddct%2Ftransformer-vocos/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mddct%2Ftransformer-vocos/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Mddct","download_url":"https://codeload.github.com/Mddct/transformer-vocos/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244566889,"owners_count":20473451,"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":[],"created_at":"2025-03-20T06:56:50.097Z","updated_at":"2026-01-04T21:05:10.780Z","avatar_url":"https://github.com/Mddct.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"## ongoing\n\n### Why vocos with transformer or conformer ?\nEasy to scale and Good control over latency and caching\n\n### Why sequence mask in gan?\nNo data length limit is required, such as 1s\n\n###  Why in wenet ？\ncache and multiple speech models are  available out of the box\n\n\n### Data Prepare\n```bash\n{\"wav\": \"/data/BAC009S0764W0121.wav\"}\n{\"wav\": \"/data/BAC009S0764W0122.wav\"}\n```\n### train\n```bash\ntrain_data = 'train.jsonl'\nmodel_dir = 'vocos/exp/2025/0.1/transformer/'\ntensorboard_dir = ${model_dir}/runs/\n\nmkdir -p $model_dir $tensorboard_dir\ntorchrun --standalone --nnodes=1 --nproc_per_node=8 vocos/main.py -- \\\n        --config vocos/configs/default.py \\\n        --config.train_data=${train_data} \\\n        --config.model_dir=${model_dir} \\\n        --config.tensorboard_dir=${tensorboard_dir} \\\n        --config.max_train_steps 1000000\n```\n\nTODO:\n- [ ] training \n  - [x] training works\n  - [x] check training process\n   - [x] generator\n   - [x] disc\n   - [ ] distill\n   - [x] resume\n   - [ ] stereo for music\n   - [x] cqt loss\n- [ ] dev benchmark etc\n- [ ] infer\n   - [x] offline\n   - [ ] chunk by chunk or frame by frame\n   - [ ] onnx\n- [ ] exmple for: cosyvoice2 and transformer-vocos\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmddct%2Ftransformer-vocos","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmddct%2Ftransformer-vocos","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmddct%2Ftransformer-vocos/lists"}