Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / babysor/MockingBird issues and pull requests
#1011 - Update README.md
Pull Request -
State: closed - Opened by babysor 12 days ago
#1009 - Update README.md
Pull Request -
State: closed - Opened by babysor 26 days ago
#1008 - 0.0.1版本web输出只有2秒钟
Issue -
State: open - Opened by CCbird about 1 month ago
- 2 comments
#1007 - Update README.md, fix a typo
Pull Request -
State: closed - Opened by BobConanDev about 1 month ago
- 1 comment
#1006 - Fit for python 3.12
Issue -
State: open - Opened by Kx-Y about 1 month ago
#1005 - Update README.md
Pull Request -
State: closed - Opened by babysor about 1 month ago
#1004 - Chore: Update TW model download link
Pull Request -
State: open - Opened by FawenYo about 2 months ago
#1002 - demo_toolbox.py无法打开
Issue -
State: open - Opened by feiyr 5 months ago
- 3 comments
#1002 - demo_toolbox.py无法打开
Issue -
State: open - Opened by feiyr 5 months ago
#1001 - encoder_preprocess.py文件
Issue -
State: open - Opened by Westbrook077 5 months ago
#999 - 请问支持api调用吗
Issue -
State: open - Opened by aqpmzngldh 6 months ago
#998 - 安装了vs最新版还是报错 (monotonic-align)
Issue -
State: open - Opened by wangerha1 6 months ago
- 3 comments
#997 - request:请教一下想法是否可行
Issue -
State: open - Opened by hch-baobei 7 months ago
#996 - 请问作者大大,encoder如何训练?
Issue -
State: open - Opened by onedotone-wei 7 months ago
- 2 comments
#995 - RuntimeError: mat1 and mat2 shapes cannot be multiplied (80x513 and 1x513)
Issue -
State: open - Opened by sbmatch 7 months ago
#994 - 预处理pre.py报错
Issue -
State: open - Opened by gaoyiyao 7 months ago
- 3 comments
#993 - NameError: name 'audio_input_selection' is not defined
Issue -
State: open - Opened by tm8888 8 months ago
#992 - 社区预先训练好的75k合成器的百度网盘链接无法下载
Issue -
State: open - Opened by womeiyoumz 8 months ago
- 2 comments
#991 - Synthesize and vocode时报错RuntimeError
Issue -
State: open - Opened by Rundll86 8 months ago
#990 - 启动python web.py无反应,小白求助
Issue -
State: open - Opened by shenfuqili 9 months ago
- 1 comment
#989 - fix requirements monotonic-align error issues-974
Pull Request -
State: closed - Opened by 1044690543 9 months ago
- 2 comments
#988 - fix-issues-963:preprocess_audio.py--The .npy file failed to save
Pull Request -
State: closed - Opened by 1044690543 9 months ago
- 1 comment
#987 - the first pretrained model url in the list cannot be opened
Issue -
State: open - Opened by liyingchunvip 10 months ago
#985 - how to solve this problem about pydantic V2? 跑代码在运行web.py时说pydantic版本不对,我使用liunx系统下跑的
Issue -
State: open - Opened by JJJJJJX1 10 months ago
- 1 comment
#984 - 有可以朗读英文和数字的模型吗
Issue -
State: open - Opened by 1144822034 10 months ago
- 1 comment
#983 - 不想每一条语音都覆盖前一条
Issue -
State: open - Opened by Ariellln 10 months ago
#982 - 没有_sources.txt这个文件'
Issue -
State: closed - Opened by Tengda520 10 months ago
#981 - 维度问题
Issue -
State: closed - Opened by Ariellln 10 months ago
#980 - 预处理数据集出现如下错误
Issue -
State: open - Opened by Sunsoar01 10 months ago
#979 - 运行 python .\pre.py G:\AISHELL-3 preprocess_audio.py预处理报错,要在transformers里边导包,可是没有这个文件夹啊
Issue -
State: open - Opened by dyhisbig 11 months ago
- 1 comment
#978 - Docker compose run failed
Issue -
State: open - Opened by aiddroid 11 months ago
#977 - windows11输入>python demo_toolbox.py后没反应,不报错
Issue -
State: open - Opened by gogoner 12 months ago
- 1 comment
#976 - 求个好心人给一个MockingBird的交流群,另外tag0.0.1版本下,运行demo_toolbox工具箱,数据集\train无法识别
Issue -
State: closed - Opened by WuzhaobinMr 12 months ago
#975 - 主要粤语训练,怎样添加MozillaCommonVoice数据集训练?
Issue -
State: open - Opened by axdwct 12 months ago
#974 - After entering this command, an error occurred: pip install -r requirements.txt
Issue -
State: open - Opened by wjf68888 12 months ago
#973 - 自定义音频效果不佳
Issue -
State: open - Opened by zhou-zhi-hong about 1 year ago
- 1 comment
#972 - MockingBird 有雲端操作嗎?
Issue -
State: open - Opened by tonkabean630 about 1 year ago
#971 - 有沒有 MockingBird Discord 交流群?
Issue -
State: open - Opened by tonkabean630 about 1 year ago
#969 - 最新的交流群或者discord社区有没有
Issue -
State: open - Opened by dorbodwolf about 1 year ago
#968 - ModuleNotFoundError: No module named 'flask.scaffold'
Issue -
State: open - Opened by a994862495 about 1 year ago
#966 - tag v0.0.1运行web.py错误(小白向)
Issue -
State: closed - Opened by hanc44 about 1 year ago
- 1 comment
#965 - linux 预处理pre.py报错 找不到npy文件
Issue -
State: open - Opened by huanglang0114 about 1 year ago
- 4 comments
#964 - cmd
Issue -
State: open - Opened by LiarScapegoat about 1 year ago
#963 - models/synthesizer/preprocess_audio.py bug
Issue -
State: open - Opened by tangzhimiao about 1 year ago
- 5 comments
#962 - 按照教程搭环境搭的心态崩溃,我是废物
Issue -
State: closed - Opened by andoloido about 1 year ago
#961 - 预处理pre.py报错
Issue -
State: closed - Opened by tangzhimiao about 1 year ago
- 2 comments
#960 - I found the results of voice synthesis are not at all like the user's voice if many user added in appa.py source code
Issue -
State: open - Opened by samen2080 about 1 year ago
#958 - 运行pre.py时报错如下,数据集的.npy文件没有生成导致的,但不知道是什么原因
Issue -
State: closed - Opened by DennisJcy about 1 year ago
- 18 comments
#957 - RuntimeError: Error(s) in loading state_dict for Tacotron: size mismatch for gst.stl.attention.W_query.weight: copying a param with shape torch.Size([512, 256]) from checkpoint, the shape in current model is torch.Size([512, 512]).
Issue -
State: open - Opened by wubinbai about 1 year ago
- 7 comments
#956 - 1 validation error for ParsingModel[Input] root -> 合成模型 none is not an allowed value (type=type_error.none.not_allowed)
Issue -
State: closed - Opened by wubinbai about 1 year ago
#955 - 生成的音频噪音有点大
Issue -
State: open - Opened by tailangjun about 1 year ago
- 3 comments
#954 - 请问data/ckpt中提供的encoder和vocoder模块的pretrained.pt是在什么数据集上进行预训练的?训练了多少个step?
Issue -
State: open - Opened by ZHUBAJIEJIU about 1 year ago
#953 - Update README.md
Pull Request -
State: closed - Opened by babysor about 1 year ago
#952 - add readme-linux-zh
Pull Request -
State: closed - Opened by SeaTidesPro about 1 year ago
- 3 comments
#951 - Create README-LINUX-CN.md
Pull Request -
State: closed - Opened by SeaTidesPro about 1 year ago
#950 - Skip embedding
Pull Request -
State: closed - Opened by babysor about 1 year ago
#949 - python demo_toolbox.py这个是不只能在本机启动?
Issue -
State: open - Opened by jcxian over 1 year ago
- 5 comments
#948 - Model shape mismatch
Issue -
State: closed - Opened by firstprayer over 1 year ago
- 1 comment
#947 - 📝 Update model download link
Pull Request -
State: closed - Opened by FawenYo over 1 year ago
- 1 comment
#946 - 有没有交流群来一波
Issue -
State: open - Opened by stars1324 over 1 year ago
- 6 comments
#945 - Update README.md
Pull Request -
State: closed - Opened by babysor over 1 year ago
#944 - Update README-CN.md
Pull Request -
State: closed - Opened by babysor over 1 year ago
#943 - 关于找不到synthesizer_train.py的朋友看这里!
Issue -
State: open - Opened by wangaocheng over 1 year ago
- 1 comment
#942 - 依赖的numpy是不是不支持np.int这样的值?
Issue -
State: open - Opened by kaleidosgu over 1 year ago
#940 - 我想问一下encoder数据集怎么生成或者在哪里下载?
Issue -
State: closed - Opened by kaleidosgu over 1 year ago
- 1 comment
#939 - Dockerfile build takes forever
Issue -
State: open - Opened by airbots over 1 year ago
#938 - An error occurs using the VC mode of the Web page
Issue -
State: open - Opened by L1590 over 1 year ago
#937 - 可以运行demo_toolbox.py,运行web.py报错
Issue -
State: open - Opened by loveannieer over 1 year ago
- 9 comments
#936 - 直接按照readme文件安装,无法运行
Issue -
State: open - Opened by sg0771 over 1 year ago
#934 - 是停更了吗
Issue -
State: open - Opened by YIZXIY over 1 year ago
- 3 comments
#933 - RuntimeError: Error(s) in loading state_dict for Tacotron: size mismatch for encoder_proj.weight: copying a param with shape torch.Size([128, 512]) from checkpoint, the shape in current model is torch.Size([128, 1024]). size mismatch for decoder.attn_rnn.weight_ih: copying a param with shape torch.Size([384, 768]) from checkpoint, the shape in current model is torch.Size([384, 1280]). size mismatch for decoder.rnn_input.weight: copying a param with shape torch.Size([1024, 640]) from checkpoint, the shape in current model is torch.Size([1024, 1152]). size mismatch for decoder.stop_proj.weight: copying a param with shape torch.Size([1, 1536]) from checkpoint, the shape in current model is torch.Size([1, 2048]).
Issue -
State: closed - Opened by Adolph3671 over 1 year ago
- 1 comment
#932 - M2芯片用conda安装依赖报错
Issue -
State: open - Opened by 993318936 over 1 year ago
- 1 comment
#931 - 预处理模型怎么生成
Issue -
State: closed - Opened by glide-the over 1 year ago
#930 - 运行pip install espnet安装失败
Issue -
State: open - Opened by DrowskoytayhulGuider over 1 year ago
- 3 comments
#929 - 自己问题
Issue -
State: closed - Opened by MySoulcutting over 1 year ago
#928 - 系统找不到指定的路径。: 'encoder\\saved_models
Issue -
State: closed - Opened by 2265290305 over 1 year ago
#927 - UnboundLocalError: local variable 'ppg' referenced before assignment
Issue -
State: open - Opened by danfouer over 1 year ago
- 2 comments
#926 - monotonic-align==0.0.3 cant install
Issue -
State: closed - Opened by 2265290305 over 1 year ago
- 1 comment
#925 - Failed building wheel for sentencepiece
Issue -
State: open - Opened by tppqt over 1 year ago
- 1 comment
#924 - 预处理 pre.py报错
Issue -
State: open - Opened by HaSaKiYasuooo over 1 year ago
- 1 comment
#923 - vocoder no PT 合成声码器没有模型产生
Issue -
State: open - Opened by HaSaKiYasuooo over 1 year ago
- 1 comment
#922 - Trainable Parameters: 0.000M正常吗
Issue -
State: open - Opened by markchen199928 over 1 year ago
- 1 comment
#920 - 使用vc转换时,转换过程报错 TypeError: unsupported operand type(s) for -: 'NoneType' and 'float'
Issue -
State: closed - Opened by zhaojigang over 1 year ago
- 2 comments
#917 - web.py/demo_toolbox.py 提示 ModuleNotFoundError: No module named 'models.encoder'
Issue -
State: open - Opened by TurboHK over 1 year ago
- 1 comment
#915 - 预训练时报错
Issue -
State: open - Opened by urcanvm over 1 year ago
- 4 comments
#912 - 执行: python demo_toolbox.py不报错,没有反应
Issue -
State: open - Opened by softpo over 1 year ago
- 4 comments
#903 - RuntimeError: Error(s) in loading state_dict for Tacotron:
Issue -
State: open - Opened by hanzawaa over 1 year ago
- 5 comments
#902 - 为什么main的新版本,我开启训练后只能使用CPU,没法使用GPU,训练速度低到 0.08setp/s
Issue -
State: open - Opened by syy7854 over 1 year ago
- 3 comments
#901 - 请问能否更新一下教程,当前代码与原有教程已不匹配
Issue -
State: open - Opened by MONUFISH over 1 year ago
- 1 comment
#899 - 模型加载错误,维度错误
Issue -
State: open - Opened by wangsheng0131 over 1 year ago
- 6 comments
#898 - 使用命令行启动方式效果出来比web和工具箱效果差很多而且还有杂音怎么处理?
Issue -
State: open - Opened by Mrxuzhongjie over 1 year ago
#897 - python3.9 运行 demo_toolbox.py 毫无反应。 web界面模式合成也会报错。
Issue -
State: open - Opened by Chinakentgao over 1 year ago
#897 - python3.9 运行 demo_toolbox.py 毫无反应。 web界面模式合成也会报错。
Issue -
State: open - Opened by Chinakentgao over 1 year ago
#896 - 生成的音频开头和结尾的停顿和渐进如何去除?
Issue -
State: open - Opened by Olivialyt over 1 year ago
- 1 comment
#895 - 怎么synthesizer_train.py都不见了,用train.py训练是跑上了,就是没有输出LOSS图也没有模型文件生成?
Issue -
State: open - Opened by sctm002 over 1 year ago
- 1 comment
#894 - AI语音克隆QQ交流群
Issue -
State: open - Opened by fengyun1801 over 1 year ago
- 1 comment
#894 - AI语音克隆QQ交流群
Issue -
State: open - Opened by fengyun1801 over 1 year ago
- 1 comment
#893 - web.py: ModuleNotFoundError: No module named 'altair.vegalite.v4'
Issue -
State: open - Opened by willin over 1 year ago
- 7 comments
#893 - web.py: ModuleNotFoundError: No module named 'altair.vegalite.v4'
Issue -
State: open - Opened by willin over 1 year ago
- 3 comments
#892 - Update FawenYo's shared model
Pull Request -
State: open - Opened by FawenYo over 1 year ago