The Wayback Machine - https://web.archive.org/web/20211221144010/https://github.com/NVIDIA/NeMo/issues
Skip to content
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.

Sign up for GitHub

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

37 Open 834 Closed
37 Open 834 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀
FastSpeech2_HiFiGAN_E2E training doesn't work bug
#3360 opened Dec 17, 2021 by mabraham
NeMo Megatron Epoch training is confusing feature request
#3353 opened Dec 16, 2021 by yidong72
@okuchaiev
ConformerCTC with input problems after ONNX conversion bug
#3352 opened Dec 16, 2021 by DanBmh
WER results are different
#3350 opened Dec 16, 2021 by andrusenkoau
8
Warning about slow loading of non-wav formats feature request
#3336 opened Dec 15, 2021 by roman-vygon
@okuchaiev
2
Running examples enc_dec_nmt.py script and getting a TypeError: expected str, bytes or os.PathLike object, not NoneType bug
#3326 opened Dec 14, 2021 by jpilaul
1
Citrinet 256 and 512 for WSJ - limited resources
#3324 opened Dec 13, 2021 by Miamoto
3
Inverse Text Normalization. Make matching between normalized and non-normalized tokens feature request
#3319 opened Dec 12, 2021 by kotikkonstantin
@ekmb @okuchaiev
Question[multi node training]
#3312 opened Dec 10, 2021 by BuaaAlban
2
trouble with dedicating multiple GPU speech_to_text_bpe bug
#3300 opened Dec 8, 2021 by sarasesar
5
Conformer training from scratch not achieving the reported WER
#3288 opened Dec 5, 2021 by kssteven418
@VahidooX
10
ECAPA TDNN pretrained fails to export ONNX - missing 'input_example' bug
#3268 opened Nov 30, 2021 by ShantanuNair
@nithinraok
1
The results cannot be reproduced using the pre-training model bug
#3267 opened Nov 30, 2021 by QzzIsCoding
@MaximumEntropy
10
Quartznet replicate some results
#3261 opened Nov 29, 2021 by Miamoto
7
What is the possibility of utilising NeMo TTS Tacotron2 for generating a new model for a native language? Please confirm whether this is possible or not as if I'm having a use case for building something for an African language to help fight Covid-19
#3254 opened Nov 27, 2021 by joekthomas
@blisc
How to train NeMo TTS Tacotron2 model from pretrained model? bug
#3249 opened Nov 26, 2021 by Sueoka-ppc
Diarization Inference Parameters feature request
#3247 opened Nov 25, 2021 by CaioRochaGoes
@nithinraok
7
Error while trying to use the NeMo's pretrained model based on TalkNet in r1.5.0 branch bug
#3212 opened Nov 18, 2021 by KnurpsBram
1
nemov1.4.0 : RuntimeError: Error(s) in loading state_dict for EncDecCTCModelBPE: size mismatch for preprocessor.featurizer.window: copying a param with shape torch.Size([40]) from checkpoint, the shape in current model is torch.Size([400]).
#3167 opened Nov 11, 2021 by apurva1to3
@VahidooX
4
index out of dimension in sd_model.diarize() "Speaker_Diarization_Inference" bug
#3137 opened Nov 4, 2021 by CaioRochaGoes
@fayejf
1
AssertionError: args is already initialized
#3064 opened Oct 27, 2021 by SonuKumari1690
DALI does not work on multi-gpu systems bug
#3042 opened Oct 22, 2021 by piraka9011
1
AttributeError: module 'nemo.collections' has no attribute 'nlp' bug
#2966 opened Oct 8, 2021 by MuhammedTech
@okuchaiev
9
AssertionError: 80, 1: /home/user/Documents/LJSpeech-1.1/wavs/LJ012-0230.wav bug
#2944 opened Oct 3, 2021 by Aasthaengg
@redoctopus
PunctuationCapitalizationModel Config: Mixed Precision Parameter not Ignored when AMP_LEVEL=O0 bug
#2887 opened Sep 24, 2021 by liaeh
@ekmb
ProTip! What’s not been updated in a month: updated:<2021-11-21.