openspeech-team/openspeech
Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.
PythonMIT
Pinned issues
Issues
- 4
---> 83 from pytorch_lightning.loggers import TensorBoardLogger, LightningLoggerBase, WandbLogger 84 except ImportError:
#223 opened by girlsending0 - 3
`OpenspeechCTCModel.forward`: `self.fc` is undefined
#230 opened by kuraga - 1
mixed precision 학습 관련
#224 opened by laetokang - 1
How to use the checkpoint to do ASR task?
#229 opened by CreepJoye - 0
Transfer Learning
#228 opened by JinMinJeon - 1
Prepare tokenizer of LibriSpeech by using sentencepiece
#227 opened by tuandattt - 5
squeezeformer 모델 학습 및 추론
#226 opened by sangheonEN - 0
- 1
XXX.pcm is not Valid!!
#222 opened by oh-young-data - 1
Importing lightning correctly
#200 opened by pfeatherstone - 3
First tasks using Openspeech
#214 opened by filbattaglia - 0
ksponspeech Dataloader returned length 0 problem
#201 opened by Cain-1019 - 2
min_pct = 1.0 / len(dataloader) error ZeroDivisionError: float division by zero
#217 opened by oh-young-data - 0
- 1
- 2
Ksponspeech Data- Number of train, validation
#192 opened by HwangJae-won - 1
학습이 되지 않습니다.
#219 opened by Seoyoung-Jo - 0
transducerloss 모델 사용시 sanity체크에서 오류가 발생해요
#218 opened by Angeriod - 0
hydra_lm_train.py 사용법
#216 opened by apg0001 - 0
- 1
학습 완료된 모델을 불러와 하나의 음성 파일을 예측하고 싶습니다
#205 opened by youngchannelforyou - 1
Import error of pytorch_lightning LightningLoggerBase
#212 opened by DevTae - 0
sp.model 경로 문제 질문드립니다
#211 opened by hbeooooooom - 5
- 0
Resuming gpu-fp16 model
#210 opened by EomSooHwan - 2
How long does the training take?
#204 opened by EomSooHwan - 0
How to modify CTC criterion / decoding algorithm?
#203 opened by EomSooHwan - 3
terminal hangs when train starts
#208 opened by tae0y - 1
Error in generate lable
#206 opened by hyungraelee - 4
초보적인 질문이라 죄송합니다
#202 opened by youngchannelforyou - 0
- 0
how to modify "openspeech/configs/train.yaml"?
#198 opened by Joll123 - 2
import error
#196 opened by Joll123 - 3
a circular import
#194 opened by ylwang0425 - 0
I met problem where i run confomerTest in test moduleImport Error: cannot import name 'OpenspeechDecoder' from partially initialized module 'openspeech.decoders' (most likely due to a circular import) (/home/wyl/openspeech/openspeech/decoders/__init__.py)
#193 opened by ylwang0425 - 1
Questions for LibriSpeech setting
#187 opened by ccyang123 - 2
Could you share the environment of yours to install?
#186 opened by sdeva14 - 0
A way to execute hydra_train.py for Ksponspeech
#191 opened by taejin0128 - 0
- 3
Unsupported criterion: CTCLoss (error)
#189 opened by ccyang123 - 6
- 9
Can't run the training examples
#185 opened by ccyang123 - 1
문장 띄어쓰기 빈칸 표시에 대해서 궁금한 점 질문 드립니다.
#184 opened by parkmy123 - 1
can't pickle dict_keys objects.
#183 opened by bobo712 - 1
relative_multi_head_attention.py 구현 수정 제안
#176 opened by LEEYOONHYUNG - 1
- 0
Apply pre-commit
#179 opened by upskyy - 2
What is the correct format of the path for datasets and manifest files (LibriSpeech)
#177 opened by AnneCCyy - 1
Using OpenSpeech With Self Downloaded Data
#175 opened by lianaling - 0
Do we have training results?
#173 opened by Peach-He