wenet-e2e / wespeaker

Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit

Repository from Github https://github.comwenet-e2e/wespeaker

wenet-e2e/wespeaker Issues

convert redimnet pt model to onnx model failed!
Updated 5 months ago4
想请问怎么生成PLDA文件
Closed 5 months ago2
Whether the subseg_cmn parameter meets the expected effect
Updated 5 months ago1
说话人日志任务好像有问题
Updated 5 months ago4
Redimnet Large Margin not improving the results
Updated 5 months ago4
很高的漏检率
Updated 6 months ago4
如何提升说话人识别的准确率
Updated 7 months ago4
如何使用GPU进行推理
Closed 7 months ago2
用c去編譯問題
Closed 7 months ago11
How to inference with pretrained models
Closed 7 months ago5
IO Bottleneck while loading data
Updated 8 months ago1
Does WeSpeaker support streaming audio?
Updated 8 months ago3
Redimnet configs for B0 and B1 models
Updated 8 months ago4
How to obtain the weights for a specific number of classes
Updated 8 months ago1
Is the evaluation metric for training not loss or accuracy, but rather EER?
Updated 8 months ago2
config. file for SimAMResNet
Updated 8 months ago2
'SimAMResNet34' is not working properly.
Updated 9 months ago3
DINO pretrained model
Closed 9 months ago3
Inquiry about the Sphereface2 loss.
Closed 9 months ago1
cnceleb-resnet支持CPU训练吗？
Closed 9 months ago1
请问说话人日志中是否需要重叠语音检测？
Updated 9 months ago1
windows上安装报错
Closed 9 months ago2
unexpected tensor: projection.weight
Closed 9 months ago6
Failed to download a model from Huggingface hub
Closed 9 months ago1
如何训练一个说话人日志模型
Updated 9 months ago4
learning rate - when big batch size
Closed 9 months ago1
wespeaker多机多卡训练
Closed 9 months ago2
Redimnet
Closed 10 months ago6
onnx 形式的预训练模型固定了帧长是有什么特别的考虑吗？
Closed 10 months ago8
想请问在说话人日志的结果怎么看对应参数
Closed 10 months ago2
请教说话人日志任务模型怎么替换成自己的模型
Closed 10 months ago4
Inquiry regarding "WARNING:root:unexpected tensor: projection.weight"
Closed 10 months ago3
请问这个问题怎么解决ImportError: cannot import name 'load_silero_vad' from 'silero_vad'
Closed 10 months ago2
MNN模型转换后对比结果错误。
Updated 10 months ago6
NeXt_TDNN_ASV
Closed a year ago1
Why use checkpoint instead of model_init during LMF
Closed a year ago3
单机多卡训练，仅GPU=0有利用率，其他卡GPU利用率=0%
Closed a year ago2
the SimAMResNet pretrain models downloads
Closed a year ago2
Download voxceleb script requests a password
Closed a year ago3
pip install {git url} doesn't install the requirements
Closed a year ago2
How to turn off Speed perturbations in LM-ft by loading pre-trained models
Closed a year ago
Compression codec augmentation ?
Updated a year ago1
FEATURE REQUEST: Add more supporting data types
Updated a year ago2
说话人日志功能求助
Closed a year ago6
Any plans to update the pypi package?
Updated a year ago5
torchrun multiprocessing error
Updated a year ago1
add_reverb_noise支持多通道rir和musan吗
Closed a year ago1
Adding ReDimNet to wespeaker
Updated a year ago2
Exporting ONNX Model with Final Class Probabilities Instead of Embeddings
Closed a year ago4
Not able to load the english model for wespeaker
Closed a year ago1