-
Notifications
You must be signed in to change notification settings - Fork 2.2k
Issues: espnet/espnet
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Unable to Pass Arguments to score_der.sh via diar.sh
Bug
bug should be fixed
#5993
opened Dec 24, 2024 by
Qingzheng-Wang
Duration mismatch of text, pitch and energy in FastSpeech2 training in ESPnet2-TTS
Question
Question
#5990
opened Dec 19, 2024 by
unilight
Devcontainer for development and experiment run.
Docker
New Features
#5986
opened Dec 18, 2024 by
Fhrozen
9 tasks
espnetez stats extraction is taking forever to run even for small samples
ESPnetEZ
Related to ESPnetEZ developments
Question
Question
#5971
opened Dec 5, 2024 by
kbramhendra
Wrong types in RttmReader & other issues
Bug
bug should be fixed
#5968
opened Dec 2, 2024 by
domklement
FileNotFoundError: [Errno 2] No such file or directory: 'exp/asr_whisper_medium_finetune_lr1e-5_adamw_wd1e-2_3epochs/config.yaml'
Bug
bug should be fixed
#5965
opened Nov 24, 2024 by
mukherjeesougata
I have some questions regarding replacing self-attention in the decoder with Mamba in the ASR model. Thank you very much for your answers.
Question
Question
#5961
opened Nov 21, 2024 by
songjie1121
Alien-like sound from inferenced audio at loss rate ~ 0.8
Question
Question
TTS
Text-to-speech
#5960
opened Nov 21, 2024 by
amarbayar
CUDA out of memory when use whisper model
Bug
bug should be fixed
#5958
opened Nov 14, 2024 by
Zilai-WANG
TypeError: unsupported operand type(s) for *: 'NoneType' and 'int'
Bug
bug should be fixed
TTS
Text-to-speech
#5956
opened Nov 14, 2024 by
CriDora
TypeError: unsupported operand type(s) for *: 'NoneType' and 'int'
Question
Question
#5955
opened Nov 14, 2024 by
CriDora
batch sizes in encoder input and decoder output
Question
Question
#5953
opened Nov 13, 2024 by
cgbhat1978
Bug in espnet-ez trainer
Bug
bug should be fixed
ESPnetEZ
Related to ESPnetEZ developments
#5949
opened Nov 12, 2024 by
juice500ml
Decoding error in DAC when using HuggingFace models
Bug
bug should be fixed
Codec
#5944
opened Nov 5, 2024 by
ashi-ta
Installation has errors with certain package versions
Installation
#5942
opened Nov 1, 2024 by
pyf98
Issues Encountered During Fine-tuning on OWSMV3.1
Bug
bug should be fixed
ESPnetEZ
Related to ESPnetEZ developments
#5927
opened Oct 10, 2024 by
teinhonglo
Help for Singing Voice Synthesis
Music
Music processing
Question
Question
#5923
opened Oct 8, 2024 by
funmolde
Streaming speaker enhancement model list
Question
Question
SE
Speech enhancement
#5920
opened Oct 5, 2024 by
GeeYangML
How can we improve our ASR model to reliably output an empty string for unintelligible speech in noisy environments?
Question
Question
#5903
opened Sep 19, 2024 by
anirpipi
Previous Next
ProTip!
no:milestone will show everything without a milestone.