Pinned issues
Issues
- 4
如何提升说话人识别的准确率
#411 opened by chenfuckthesky - 2
如何使用GPU进行推理
#409 opened by chenfuckthesky - 11
- 5
How to inference with pretrained models
#360 opened by freshpearYoon - 1
IO Bottleneck while loading data
#402 opened by chnk58hoang - 3
Does WeSpeaker support streaming audio?
#401 opened by zxy719 - 4
Redimnet configs for B0 and B1 models
#400 opened by vandana-rajan - 1
- 2
Is the evaluation metric for training not loss or accuracy, but rather EER?
#396 opened by NathanJHLee - 2
config. file for SimAMResNet
#365 opened by BongkiLee - 3
'SimAMResNet34' is not working properly.
#391 opened by NathanJHLee - 3
DINO pretrained model
#378 opened by hsiaohan0827 - 1
Inquiry about the Sphereface2 loss.
#374 opened by JuseokSeong - 1
cnceleb-resnet支持CPU训练吗?
#393 opened by wjddd - 1
请问说话人日志中是否需要重叠语音检测?
#390 opened by wcqy-ye - 2
windows上安装报错
#362 opened by yumianhuli1 - 6
unexpected tensor: projection.weight
#385 opened by Genesis1231 - 1
Failed to download a model from Huggingface hub
#392 opened by rose-jinyang - 4
如何训练一个说话人日志模型
#363 opened by wwbnjsace - 1
learning rate - when big batch size
#388 opened by MM-0712 - 2
Unable to load shard
#338 opened by mrjunjieli - 2
wespeaker多机多卡训练
#383 opened by wcqy-ye - 6
Redimnet
#355 opened by freshpearYoon - 8
onnx 形式的预训练模型固定了帧长是有什么特别的考虑吗?
#380 opened by songfuture - 2
想请问在说话人日志的结果怎么看对应参数
#387 opened by wcqy-ye - 4
请教说话人日志任务模型怎么替换成自己的模型
#386 opened by wcqy-ye - 3
- 2
- 6
MNN模型转换后对比结果错误。
#350 opened by cwp-wind - 1
NeXt_TDNN_ASV
#379 opened by xczhusuda - 3
Why use checkpoint instead of model_init during LMF
#376 opened by didi1233 - 2
单机多卡训练,仅GPU=0有利用率,其他卡GPU利用率=0%
#373 opened by YMLLG - 2
the SimAMResNet pretrain models downloads
#369 opened by smehrabikia - 3
Download voxceleb script requests a password
#368 opened by tcourat - 2
- 0
- 1
Compression codec augmentation ?
#364 opened by tcourat - 3
Would it be able to feed in the audio itself for classifier_skid.compute_similarity function instead of giving the audio's path?
#331 opened by DeliJingyiC - 2
FEATURE REQUEST: Add more supporting data types
#345 opened by Genesis1231 - 3
tritonserver install problem.
#334 opened by noname111234 - 6
- 5
Any plans to update the pypi package?
#354 opened by MiniXC - 1
torchrun multiprocessing error
#353 opened by UzumakiAmir - 1
add_reverb_noise支持多通道rir和musan吗
#348 opened by woodyzhuo - 2
Adding ReDimNet to wespeaker
#341 opened by Spectra456 - 4
- 1
Not able to load the english model for wespeaker
#343 opened by Racketycomic - 2
Got AttributeError: 'RecursiveScriptModule' object has no attribute 'get_speech_timestamps' when running wespeaker diarization
#335 opened by ryanwong00 - 0
Updates Plan
#337 opened by wsstriving - 3
Could not find a version that satisfies the requirement silero-vad error while installing wespeaker
#332 opened by Racketycomic