8000 Issues · s3prl/s3prl · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
8000

Issues: s3prl/s3prl

Beta
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

56 Open 347 Closed
56 Open 347 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

extra tokens are not optimised by CTC loss but used as targets for model to predict
#570 opened May 2, 2025 by wenjie-p
Use custom hubert as teacher to train a hubert distilled
#569 opened Apr 26, 2025 by eloi-tavus
1
No Access to Fluent Speech Commands Dataset
#567 opened Mar 9, 2025 by omertalmi5
Finetune the upstream
#561 opened Dec 9, 2024 by LIN12955
Finetuning Distil Hubert Model for emotion recognition
#558 opened Sep 12, 2024 by staru09
Looking for a Model Zoo for Downstream Tasks
#557 opened Sep 10, 2024 by twmht
1
Performance mismatch between the train and inference phases (Downstream task: Speech Enhancement)
#552 opened Aug 23, 2024 by seorim0
A way to save and load the output of upstream model for speedup
#546 opened Jun 19, 2024 by shreyas2206
3
run vq_apc pretrain failed
#542 opened Jun 4, 2024 by moodeerf
@andi611
3
How to extract weighted sum SSL representations from an audio dataset?
#539 opened May 6, 2024 by mukherjeesougata
What is the accept rate in the VC task evaluation output?
#530 opened Feb 5, 2024 by raotnameh
1
ValueError: mutable default <class 's3prl.upstream.roberta.roberta_model.EncDecBaseConfig'> for field encoder is not allowed: use default_factory
#522 opened Dec 21, 2023 by haoyunlf
6
Different upstream and downstream learning rates
#521 opened Dec 14, 2023 by xt0r3-Cambridge
1
University Work: Mispronunciation Detection
#508 opened Oct 5, 2023 by xt0r3-Cambridge
3
support whisper as upstream models
#494 opened Jul 14, 2023 by talallc
1
Port problem when using DDP (more than 2 experiments on same server)
#483 opened May 21, 2023 by kaen2891
1
KeyError for testing my own dataset with wav2vec
#481 opened May 4, 2023 by Arthurwyf
Finetuning SUPERB on custom dataset with 395 classes
#480 opened May 2, 2023 by Sreeni1204
Is DDP enabled for speaker identification using wav2vec2?
#479 opened May 2, 2023 by Sreeni1204
4
Bad results with custom training data in a2o-vc-vcc2020 voice conversion task
#477 opened Apr 16, 2023 by moaazassali
RuntimeError: stft requires the return_complex parameter be given for real inputs, and will further require that return_complex=True in a future PyTorch release.
#475 opened Apr 4, 2023 by finquick
3
customize upstream model
#474 opened Mar 23, 2023 by Qinnns
2
My SID and ASV results of the data2vec-base model are different from the benchmark
#469 opened Mar 14, 2023 by qijieshao
8
Enable fp16 in downstream/runner.py
#465 opened Mar 3, 2023 by GiscardBiamby
2
Can Not Download MOS Prediction Datasets VCC2016 and VCC2018
#464 opened Mar 2, 2023 by MingjieChen
@RayTzeng
ProTip! Mix and match filters to narrow down what you’re looking for.
0