Skip to content

Issues: sanchit-gandhi/whisper-jax

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

25 Open 9 Closed
25 Open 9 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 Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Process Killed without any Error
#36 opened Apr 24, 2023 by BATspock
Selecting Language Manually e.g. Hindi Language
#35 opened Apr 24, 2023 by di37
AttributeError: module 'jax.tree_util' has no attribute 'register_pytree_with_keys_class'
#34 opened Apr 23, 2023 by silvacarl2
5
Looks like no way to use on windows
#33 opened Apr 23, 2023 by FurkanGozukara
2
How to save txt vtt and srt outputs? how to set beam_size, initial_prompt, best_of and other parameters
#31 opened Apr 23, 2023 by FurkanGozukara
No GPU/TPU found, falling back to CPU.
#30 opened Apr 23, 2023 by ontheway-arch
1
[Bug]Invalid URL 'None': No schema supplied
#28 opened Apr 23, 2023 by mriamnobody
ValueError: ffmpeg was not found but is required to load audio files from filename
#27 opened Apr 23, 2023 by mriamnobody
1
[Suggestion]Please add a requirements.txt file for smooth installation
#26 opened Apr 23, 2023 by mriamnobody
Speaker diarization?
#25 opened Apr 23, 2023 by RLinnae
3
Enhancement: Add the WebUI for kaggle
#24 opened Apr 22, 2023 by faisalhr1997
Model providing not an accurate transcription , mixing some other language .
#23 opened Apr 22, 2023 by Bharadwajsai-121
ability to provide initial_prompt
#21 opened Apr 22, 2023 by thomasmol
Performance on M1 chips compared to PyTorch implementation?
#20 opened Apr 22, 2023 by andrewschreiber
KeyError: 'tokens'
#19 opened Apr 22, 2023 by syedmustafa54
How to indicate the input audio file?
#18 opened Apr 21, 2023 by remybonnav
Where to put model in local install
#17 opened Apr 21, 2023 by remybonnav
cannot import name 'dot_product_attention_weights' from 'flax.linen.attention
#16 opened Apr 21, 2023 by darkzbaron
1
Bug: Numpy array as input
#15 opened Apr 21, 2023 by knoriy
4
Add speed comparison to whisper.cpp
#12 opened Apr 21, 2023 by TheKnarf
1
is it usable with LoRA fine-tuned whisper?
#11 opened Apr 21, 2023 by Boulaouaney
2
Default test files are generating repeating text / hallucinating
#9 opened Apr 21, 2023 by greenman2
1
CUDA out of memory
#7 opened Apr 20, 2023 by Tronic
3
Recreate Benchmarks on A100
#5 opened Apr 20, 2023 by AndrewZhaoLuo
2
realtime transcriptions
#3 opened Apr 20, 2023 by eschmidbauer
2
ProTip! Exclude everything labeled bug with -label:bug.