Wenet目前可以支持在单机单卡和单机多卡上训练,后续会开放多机多卡的功能。 动态chunk训练 Wenet的提出了一套动态chunk的训练方法,该方法在训练时,随机为样本选择不同的chunk大小,从而允许一个模型可处理不同chunk大小的输入,当场景不需要流式识别是,可以使用整句长度作为chunk大小,以获得最佳识别性能。当场景需要流...
git clone https://github.com/wenet-e2e/wenet.git Install Conda: please seehttps://docs.conda.io/en/latest/miniconda.html Create Conda env: conda create -n wenet python=3.10 conda activate wenet conda install conda-forge::sox Install CUDA: please follow thislink, It's recommended to install...
WenetSpeech refers a lot of work ofGigaSpeech, and we thank Jiayu Du and Guoguo Chen for their suggestions on this work. We thank Tencent Ethereal Audio Lab and Xi'an Future AI Innovation Center for providing hosting service for WenetSpeech. We also thankMindSporefor the support of this work...
墨菲安全对开源项目wenet-e2e/WeTextProcessing进行了软件成分分析,发现引入开源组件 3 个,相关许可证 1 类,其中存在漏洞的缺陷组件 0 个。 安全风险信息 目前暂未识别到安全风险,安全风险后续仍需持续关注。 许可证合规风险信息 项目中涉及到的许可证类型:1 种; ...
已有帐号?立即登录 main 克隆/下载 git config --global user.name userName git config --global user.email userEmail 分支1 标签0 贡献代码 同步代码 create_futureadd fixedf0d1f5e2年前 132 次提交 提交取消 提示:由于 Git 不支持空文件夾,创建文件夹后会生成空的 .keep 文件 ...
wenet-e2e/opencpop wenet-e2e/opencpopPublic NotificationsYou must be signed in to change notification settings Fork10 Star211 master BranchesTags Code Latest commit Cannot retrieve latest commit at this time. History 8 Commits README Opencpop
git clone https://github.com/wenet-e2e/wekws.git Install Conda: please seehttps://docs.conda.io/en/latest/miniconda.html Create Conda env: conda create -n wekws python=3.8 conda activate wekws pip install -r requirements.txt conda install pytorch=1.10.0 torchaudio=0.10.0 cudatoolkit=11.1...
Issues: wenet-e2e/wenet 中文开源语音大模型计划 #2097 opened Nov 1, 2023 by xingchensong Open 49 [feats/llm]语音大模型背景下的llm集成 #2142 opened Nov 14, 2023 by Mddct Open 18 Labels 15 Milestones 0 New issue Clear current search query, filters, and sorts 1 Open 1 Closed...
Issues: wenet-e2e/wenet Open50 #2142 openedNov 14, 2023byMddct Open18 LabelsMilestones New issue 10 Open1,034 Closed Author Label Projects Milestones Assignee Sort 👍👎😄🎉😕 ️🚀👀 Issues list Questions of the errors during Fine Tune / 求助Fine Tune过程中碰到的问题...
Wenet2.2.1 version, the test set is librispeech's test_clean, the test results, the official pre-training model u2++conformer, two questions: recognize.py uses attention mode to decode, and a large number of <sos/eos> symbols appear. <so...