Skip to content

Issues: shashikg/WhisperS2T

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

27 Open 35 Closed
27 Open 35 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

Invalid handle. Cannot load symbol cudnnCreateTensorDescriptor Error
#76 opened Nov 2, 2024 by andriken
Are utterance-level timings available?
#75 opened Oct 18, 2024 by abresch
Whisper HF does not work
#73 opened Oct 2, 2024 by eschmidbauer
Add Lora Dynamic switching for inference
#71 opened Aug 14, 2024 by Jeevi10
4
bad_word_list argument for TRT backend is ignored
#69 opened Aug 1, 2024 by yv0vaa
data/KINCAID46/manifest_wav.tsv?
#68 opened Jul 30, 2024 by silvacarl2
is there a bench mark report for whisper large v3 model ?
#67 opened Jul 30, 2024 by fastfading
Scripts for running WER benchmarks are missing
#66 opened Jul 19, 2024 by stri8ed
Timeline has no milliseconds
#64 opened Jun 9, 2024 by zx3777
initial_prompt for tensorrt backend
#62 opened May 21, 2024 by draganjovanovich
1
Randomly getting error while generating word timestamps
#59 opened Apr 9, 2024 by rahulmate
3
how to convert a custom whisper in openai format or HF whisper model to TensorRT based backend ? enhancement New feature or request
#58 opened Apr 8, 2024 by StephennFernandes
@shashikg
21
'RuntimeError: stft input and window must be on the same device but got self on cuda:1 and window on cuda:0' when specify "device_index = 1" of "whisper_s2t.load_model" bug Something isn't working
#56 opened Apr 1, 2024 by JH90iOS
@shashikg
1
Heuristics
#55 opened Mar 31, 2024 by ngcheeyuan
[large-v3] Error during transcription: Invalid input features shape: expected an input with shape (3, 80, 3000), but got an input with shape (3, 128, 3000) instead bug Something isn't working
#51 opened Mar 20, 2024 by twardoch
5
Handle batch processing when few files fails in the whole batch bug Something isn't working
#50 opened Mar 11, 2024 by BBC-Esq
3
problems with using huggingface flash attention 2 backend on windows bug Something isn't working
#48 opened Mar 3, 2024 by BBC-Esq
depricated flag for flash attention 2 with huggingface backend
#39 opened Feb 25, 2024 by BBC-Esq
@shashikg
1
speaker diarization
#35 opened Feb 22, 2024 by tristan-mcinnis
1
other backends such as whisper.cpp?
#33 opened Feb 22, 2024 by BBC-Esq
7
Please support whisper medium and medium.en in tensorrt-llm backend
#30 opened Feb 21, 2024 by colinator
1
1
Is it possible support real-time transcription with websockets?
#25 opened Feb 21, 2024 by joaogabrieljunq
7
TensorRT - avg_logprob enhancement New feature or request
#22 opened Feb 20, 2024 by OValery16
4
Reproducing benchmarks
#11 opened Feb 5, 2024 by sanchit-gandhi
3
Suggestion to deal with omission of periods
#9 opened Jan 31, 2024 by busdriverbuddha
7
ProTip! Adding no:label will show everything without a label.