modelscope/3D-Speaker

Issues

• [ENG] CAM++ EER Results on VoxCeleb-O/E/H datasets

  #149 opened 2 months ago by K1ndWha1e
  4

• Using CAM++ for Speaker Embeddings on 24kHz LibriTTS Data: Sampling Rate Adjustment for MFCC Calculation?

  #147 opened 2 months ago by xjf-303
  1

• 关于train.csv

  #148 opened 2 months ago by huayu-2049
  2

• 如何微调ERes2NetV2_w24s4ep4模型

  #145 opened 2 months ago by kwaihua
  2

• Confidence value export possible?

  #144 opened 2 months ago by Tortoise17
  1

• 训练数据替换和断点恢复训练

  #143 opened 2 months ago by zhangzh16
  1

• The voxceleb dataset is not available for download

  #142 opened 3 months ago by gray5wolf
  1

• ModuleNotFoundError: No module named 'datasets'

  #140 opened 3 months ago by speechchemistry
  4

• Offline models

  #141 opened 3 months ago by Tortoise17
  0

• CAM++ onnx infer与pytorch infer结果不一致

  #139 opened 3 months ago by njzheng
  4

• 200k speakers 的数据集分布

  #138 opened 3 months ago by zhangyike
  1

• 与FunClip在说话人识别上的比较

  #137 opened 3 months ago by yumianhuli1
  4

• onnx模型导出报错

  #136 opened 3 months ago by Square-of-W
  1

• Recommended threshold of cosine distance of two speeches

  #135 opened 4 months ago by hkingtswcbyy
  1

• About ASR with Speaker Diarization pipeline

  #134 opened 4 months ago by yChenN1
  4

• 语种识别，怎么将modelscope里的模型对应上

  #133 opened 4 months ago by wjyfelicity
  1

• 小白请教一下这段代码

  #132 opened 4 months ago by Juelianqvq
  3

• speakerlab/process/augmentation.py addnoise function has undefined symbol

  #130 opened 4 months ago by laishuzhong
  1

• 如何使用自己的声纹文件进行模型训练

  #129 opened 4 months ago by smengfei
  1

• 请教language-identification语料时数问题

  #123 opened 5 months ago by jeremy110
  12

• 训练CAM++时的问题

  #127 opened 5 months ago by HaoFengyuan
  1

• 请教多模态说话人日志处理问题

  #125 opened 5 months ago by liuruoling
  1

• 训练问题

  #124 opened 5 months ago by Onlyooo
  3

• GPU requirement for sv-eres2netv2

  #122 opened 6 months ago by Tortoise17
  3

• Numbers of speakers

  #121 opened 6 months ago by Tortoise17
  1

• Inference index info in indentification from trained model

  #120 opened 6 months ago by Tortoise17
  5

• Assertion error

  #119 opened 6 months ago by Tortoise17
  0

• 关于ERes2Net_VOX模型的效果问题

  #117 opened 6 months ago by Yaodada12
  4

• 流式说话人识别可以实现吗？

  #116 opened 6 months ago by zzk2021
  1

• SELF-DISTILLATION NETWORK WITH ENSEMBLE PROTOTYPES: LEARNING ROBUST SPEAKER REPRESENTATIONS WITHOUT SUPERVISION

  #115 opened 7 months ago by gancx
  2

• For ERes2NetV2 performance on short-duration wavs

  #111 opened 7 months ago by JiJiJiang
  2

• 客户端没有所需的特权

  #107 opened 8 months ago by aeakcemn
  0

• 有没有ERes2NetV2，m_channels = 32，在200k-Spkrs上面训练的模型发布？

  #105 opened 8 months ago by bhpugongying
  4

• 数据集

  #103 opened 8 months ago by wangsheng3
  3

• support real-time speaker diarization?

  #99 opened 8 months ago by sunnnnnnnny
  1

• 关于人脸相关模型输入通道的问题。

  #95 opened 8 months ago by hao-qiang
  1

• 关于exp decrease learning schedule

  #89 opened 9 months ago by JINzezhong7
  2

• 关于切分subseg的问题

  #93 opened 8 months ago by hao-qiang
  1

• 使用speaker diarization结合视频的DER结果效果比单音频的还要差，请问这可以微调嘛？

  #90 opened 8 months ago by Coconut059
  3

• 使用speaker diarization结合视频的DER结果效果比单音频的还要差，请问这可以微调嘛？

  #91 opened 9 months ago by Coconut059
  0

• 打包的exe执行时报错Error loading model: 'speaker-verification is not in the pipelines registry group speaker-verification. Please make sure the correct version of ModelScope library is used.'

  #87 opened 9 months ago by eugeneYz
  1

• modelscope如何调用自己训练的模型

  #86 opened 9 months ago by canglangzhishuiz
  3

• sv-eres2net训练异常

  #85 opened 9 months ago by canglangzhishuiz
  6

• speaker-diarization进行说话人识别的时候，一小时的音频最后十分钟缺失，text里面最大时间戳是50分钟左右

  #84 opened 9 months ago by xztzmr
  2

• ERes2Net训练问题

  #83 opened 9 months ago by YiChen1997
  4

• eres2net模型是否支持mp3

  #82 opened 9 months ago by xztzmr
  2

• 打包成exe执行的时候报错缺少文件或文件夹'C:\\Users\\82437\lAppData\\Locall\\Temp\\ MEI32122\lfuasr\\version.txt'

  #81 opened 9 months ago by eugeneYz
  1

• sv-rdino trainning data.

  #80 opened 9 months ago by hcfeng201
  1

• Inquiry about training large-scale data

  #79 opened 9 months ago by axuan731
  1

• information about room acoustics in the dataset

  #78 opened 10 months ago by sivannavis
  1