Giters
hitachi-speech
/
EEND
End-to-End Neural Diarization
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
368
Watchers:
17
Issues:
46
Forks:
57
hitachi-speech/EEND Issues
cant start training
Updated
6 months ago
Comments count
37
Run log is empty
Updated
6 months ago
Comments count
1
运行日志为空,gpu使用率为0
Updated
6 months ago
The problem about to run.sh
Updated
6 months ago
Comments count
3
Question about CUDA toolkit version
Closed
a year ago
Comments count
2
How to Run Callhome
Updated
9 months ago
Comments count
4
Question about pit loss calculation in EDA-EEND model
Updated
a year ago
Requesting for the 2-spk callhome result.
Closed
2 years ago
Smoothing the activations at the output of the transformer
Updated
2 years ago
?How does scoring works in run_eda.sh?
Updated
2 years ago
Comments count
1
can't find file . parse_options.sh
Closed
4 years ago
Comments count
2
PositionalEncoding does not used?
Closed
2 years ago
Comments count
1
Have you tried this on the AMI dataset?
Closed
2 years ago
Comments count
3
The result of BLSTM is better than Transformer?
Updated
3 years ago
The question about running lstm.sh
Updated
3 years ago
Comments count
2
about the "get_free_gpus()" function
Updated
3 years ago
Comments count
1
Question about infer.py for EDA
Updated
3 years ago
Comments count
1
Restrict the number of cores being used during inference
Updated
3 years ago
About the train loss
Closed
3 years ago
When I reproduced the code, I got the following error when running ./run.sh, what should I do?
Updated
3 years ago
Trained custom data on mini_librispeech recipe but inference just gives 1 speaker for whole audio file.
Updated
3 years ago
Comments count
1
Why are we using "load_segments_rechash" function when loading the segments file? Why are we not using "load_segments", Its causing key error in the pipeline.
Updated
3 years ago
Issues about data preparation
Updated
3 years ago
about data prepare
Updated
3 years ago
Comments count
1
Adaptation error on AMI data: Invalid shape for monophonic audio: ndim=2, shape=(400000, 2)
Closed
3 years ago
Comments count
1
Adaptation Error
Updated
3 years ago
Comments count
2
Experiment results on multiple speakers dataset
Closed
3 years ago
Comments count
5
I want to know how to prepare my own data?
Closed
3 years ago
Comments count
3
run_prepare_shared.sh error
Closed
3 years ago
about the input_dim in infer stage
Closed
3 years ago
Comments count
2
The SA-EEND-EDA experiment DER result on mini_librispeech
Closed
3 years ago
Comments count
3
Makefile cupy-cuda chainer
Closed
3 years ago
Comments count
2
Can this code support multi-gpu training?
Closed
3 years ago
Comments count
1
Unable to identify speaker cluster from generated RTTM
Closed
3 years ago
Comments count
3
What are the two numbers at the end of each line in "segment" file?
Closed
3 years ago
How to evaluate long records with SA-EED.
Closed
3 years ago
Comments count
1
What is the extension for files like segments, utt2spk?
Closed
4 years ago
Confusion about the calculation of DER
Closed
4 years ago
Comments count
2
Confusion about the store of uttid
Closed
4 years ago
Comments count
2
Licensing Information
Closed
4 years ago
How to resume training?
Closed
4 years ago
Comments count
1
Question about shuffle
Closed
4 years ago
Comments count
2
High memory usage
Updated
4 years ago
Any timeline to support the newly-published papers?
Updated
4 years ago
Tcl_AsyncDelete error
Closed
5 years ago
Comments count
3
best_score.sh file is missing
Closed
5 years ago
Comments count
1