{"id":19054740,"url":"https://github.com/ssbuild/asr_seq2seq_finetuning","last_synced_at":"2025-07-17T07:34:41.962Z","repository":{"id":203477992,"uuid":"707977609","full_name":"ssbuild/asr_seq2seq_finetuning","owner":"ssbuild","description":null,"archived":false,"fork":false,"pushed_at":"2023-11-03T07:15:23.000Z","size":472,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"dev","last_synced_at":"2025-02-22T01:19:59.987Z","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":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ssbuild.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}},"created_at":"2023-10-21T06:35:50.000Z","updated_at":"2023-10-25T08:09:06.000Z","dependencies_parsed_at":null,"dependency_job_id":"76dc4d03-c6d7-4a3b-9b4d-dee82f942da9","html_url":"https://github.com/ssbuild/asr_seq2seq_finetuning","commit_stats":null,"previous_names":["ssbuild/asr_seq2seq_finetuning"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ssbuild/asr_seq2seq_finetuning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ssbuild%2Fasr_seq2seq_finetuning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ssbuild%2Fasr_seq2seq_finetuning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ssbuild%2Fasr_seq2seq_finetuning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ssbuild%2Fasr_seq2seq_finetuning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ssbuild","download_url":"https://codeload.github.com/ssbuild/asr_seq2seq_finetuning/tar.gz/refs/heads/dev","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ssbuild%2Fasr_seq2seq_finetuning/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265577771,"owners_count":23791221,"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":"2024-11-08T23:39:40.273Z","updated_at":"2025-07-17T07:34:41.946Z","avatar_url":"https://github.com/ssbuild.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## update information\r\n   - [deep_training](https://github.com/ssbuild/deep_training)\r\n\r\n```text\r\n    10-24 initial asr seq2seq\r\n```\r\n   \r\n\r\n## install\r\n  - pip install -U -r requirements.txt\r\n  - 如果无法安装， 可以切换官方源 pip install -i https://pypi.org/simple -U -r requirements.txt\r\n\r\n\r\n\r\n## weigtht select one is suitable for you\r\n支持且不限于以下权重    \r\n- [whisper-large-v2](https://huggingface.co/openai/whisper-large-v2)\r\n- [whisper-large](https://huggingface.co/openai/whisper-large)\r\n- [whisper-base](https://huggingface.co/openai/whisper-base)\r\n- [whisper-small](https://huggingface.co/openai/whisper-small)\r\n- [whisper-tiny](https://huggingface.co/openai/whisper-tiny)\r\n- [speecht5_asr](https://huggingface.co/microsoft/speecht5_asr)\r\n## data sample\r\n- open_data https://github.com/ssbuild/open_data\r\n- common_voice_11_0 https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0\r\n- common_voice https://huggingface.co/datasets/common_voice\r\n   \r\n单条数据示例\r\n```json\r\n{\r\n  \"path\": \"../zh-CN_train_0/common_voice_zh-CN_33211332.mp3\",\r\n  \"sentence\": \"性喜温暖润湿气候且耐寒。\",\r\n  \"locale\": \"zh-CN\"\r\n}\r\n```\r\n\r\n\r\n\r\n## infer\r\n    # infer_finetuning.py 推理微调模型\r\n    # infer_lora_finetuning.py 推理微调模型\r\n     python infer_finetuning.py\r\n\r\n\r\n\r\n## training\r\n```text\r\n    # 制作数据\r\n    cd scripts\r\n    bash train_full.sh -m dataset \r\n    or\r\n    bash train_lora.sh -m dataset \r\n    or\r\n    bash train_ptv2.sh -m dataset \r\n    \r\n    注: num_process_worker 为多进程制作数据 ， 如果数据量较大 ， 适当调大至cpu数量\r\n    dataHelper.make_dataset_with_args(data_args.train_file,mixed_data=False, shuffle=True,mode='train',num_process_worker=0)\r\n    \r\n    # 全参数训练 \r\n        bash train_full.sh -m train\r\n        \r\n    # lora adalora ia3 \r\n        bash train_lora.sh -m train\r\n        \r\n    # ptv2\r\n        bash train_ptv2.sh -m train\r\n```\r\n   \r\n\r\n## 训练参数\r\n[训练参数](args.MD)\r\n\r\n## 友情链接\r\n\r\n- [pytorch-task-example](https://github.com/ssbuild/pytorch-task-example)\r\n- [tf-task-example](https://github.com/ssbuild/tf-task-example)\r\n- [chatmoss_finetuning](https://github.com/ssbuild/chatmoss_finetuning)\r\n- [chatglm_finetuning](https://github.com/ssbuild/chatglm_finetuning)\r\n- [t5_finetuning](https://github.com/ssbuild/t5_finetuning)\r\n- [llm_finetuning](https://github.com/ssbuild/llm_finetuning)\r\n- [llm_rlhf](https://github.com/ssbuild/llm_rlhf)\r\n- [chatglm_rlhf](https://github.com/ssbuild/chatglm_rlhf)\r\n- [t5_rlhf](https://github.com/ssbuild/t5_rlhf)\r\n- [rwkv_finetuning](https://github.com/ssbuild/rwkv_finetuning)\r\n- [baichuan_finetuning](https://github.com/ssbuild/baichuan_finetuning)\r\n\r\n## \r\n    纯粹而干净的代码\r\n\r\n## Star History\r\n\r\n[![Star History Chart](https://api.star-history.com/svg?repos=ssbuild/asr_seq2seq_finetuning\u0026type=Date)](https://star-history.com/#ssbuild/asr_seq2seq_finetuning\u0026Date)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fssbuild%2Fasr_seq2seq_finetuning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fssbuild%2Fasr_seq2seq_finetuning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fssbuild%2Fasr_seq2seq_finetuning/lists"}