Skip to content

Issues: k2-fsa/icefall

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

158 Open 484 Closed
158 Open 484 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Zipformer Training Issues:Gradient too small and cuda out of memory issue
#1751 opened Sep 10, 2024 by bsshruthi22
7
devision by zero
#1737 opened Sep 4, 2024 by Airgods
2
pad_length in streaming decode
#1736 opened Sep 4, 2024 by 1215thebqtic
No duration or confidence info for alignments
#1735 opened Sep 2, 2024 by AhmedSalah98
2
Nan outputs from encoder
#1731 opened Aug 22, 2024 by Manjunath-mlp
12
LLM post processing
#1729 opened Aug 22, 2024 by AlexandderGorodetski
[Transducer Loss] Why not normalize transducer loss
#1726 opened Aug 19, 2024 by ncakhoa
Zipformer-s model training problem , thanks!
#1720 opened Aug 15, 2024 by TszSimLaw
Early Stopping of Token Generation in Streaming Model Training
#1717 opened Aug 13, 2024 by Triplecq
27
Training with disfluencies in speech
#1701 opened Jul 24, 2024 by duhtapioca
Training speed is not improved by using a better GPU
#1698 opened Jul 20, 2024 by SongLi89
14
get data manifest for SSL recipe
#1697 opened Jul 19, 2024 by sanjuktasr
Lower Frequency Video Recognition
#1695 opened Jul 18, 2024 by kerolos
lilcom error occurs when using kespeech training: lilcom: Length of string was too short
#1688 opened Jul 12, 2024 by kellkwang
7
Cannot download reazonspeech dataset
#1675 opened Jul 1, 2024 by hoangtm-aimesoft
4
[Help needed] Support https://huggingface.co/datasets/Alex-Song/MSR-86K
#1674 opened Jul 1, 2024 by csukuangfj
2
How to reduce memory when decoding on CPU?
#1672 opened Jun 29, 2024 by tz301
8
fast_beam_search_nbest gives very high WER compared to fast_beam_search and greedy.
#1668 opened Jun 24, 2024 by chirag-augnito
2
Non-streaming Conformer model with pruned_rnnt_loss always emits the first non-blank characters on the very first frames.
#1666 opened Jun 24, 2024 by guoyifan97
1
Using my own data to train pruned_transducer_stateless7_ctc_bs, encountered an error
#1659 opened Jun 20, 2024 by kellkwang
how to decrease the right chunk size when using zipformer model？
#1644 opened Jun 4, 2024 by csf123123
Why unique lexicon is needed in Chinese ASR, but not in English ASR?
#1639 opened May 31, 2024 by yzchen563
kaldifeat installation error
#1638 opened May 26, 2024 by AlexandderGorodetski
2
Different Training Loss with Single Node (8 GPUs) vs. Two Nodes (4 GPUs Each)
#1628 opened May 20, 2024 by dohe0342
pytorch ver. >=2.1.0 breaks compatibility with all conformer_ctc recipes
#1610 opened Apr 28, 2024 by JinZr
ProTip! Mix and match filters to narrow down what you’re looking for.