{"id":23725995,"url":"https://github.com/voidful/hubert-pretrain","last_synced_at":"2025-10-04T17:16:54.563Z","repository":{"id":182243814,"uuid":"663383632","full_name":"voidful/hubert-pretrain","owner":"voidful","description":"using huggingface trainer to pre-train hubert","archived":false,"fork":false,"pushed_at":"2023-10-26T13:27:01.000Z","size":9,"stargazers_count":2,"open_issues_count":1,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-12-31T00:17:59.174Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/voidful.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}},"created_at":"2023-07-07T07:09:38.000Z","updated_at":"2023-11-25T14:29:14.000Z","dependencies_parsed_at":"2023-07-19T09:06:35.591Z","dependency_job_id":null,"html_url":"https://github.com/voidful/hubert-pretrain","commit_stats":null,"previous_names":["voidful/hubert-pretrain"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2Fhubert-pretrain","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2Fhubert-pretrain/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2Fhubert-pretrain/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2Fhubert-pretrain/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/voidful","download_url":"https://codeload.github.com/voidful/hubert-pretrain/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239824981,"owners_count":19703194,"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":"2024-12-31T00:18:07.799Z","updated_at":"2025-10-04T17:16:54.442Z","avatar_url":"https://github.com/voidful.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"```shell\nWANDB_MODE=disabled python train.py --tokenize_config facebook/hubert-large-ls960-ft --model_config \\\nntu-spml/distilhubert --group_by_length --train_set hf-internal-testing/librispeech_asr_dummy --train_split validation \\\n--train_subset clean --test_split validation --test_subset clean --learning_rate 0.0003 --batch 30 --logging_steps 10 \\\n--eval_steps 60 --epoch 150 --use_auth_token True --output_dir ./model_test --overwrite_output_dir --batch 1 \\\n--vocab_size 500\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvoidful%2Fhubert-pretrain","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvoidful%2Fhubert-pretrain","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvoidful%2Fhubert-pretrain/lists"}