YuanGongND whisper-at issues

YuanGongND / whisper-at

Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong Audio Event Taggers"

BSD 2-Clause "Simplified" License

318 stars 25 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

[Bug] whisper-at dependency installation issue Linux

#34 3manifold opened 6 days ago
0
Minimal hardware for training?

#33 EtienneAb3d opened 1 month ago
0
Can Whisper-AT perform AR tasks？

#32 Furtherking opened 2 months ago
1
Do we need to change anything at the whisper_at when we load a fine-tuned model?

#31 sykuann opened 2 months ago
0
the question about finetune whisper

#30 LithiumZhou opened 3 months ago
1
the question about dataset feature

#29 LithiumZhou opened 4 months ago
5
Using custom trained whisper-at model

#28 himacks opened 5 months ago
1
Can this be used to mute non speech parts of an audio?

#27 orionflame opened 6 months ago
3
ResolutionImpossible error

#26 orionflame opened 6 months ago
9
as20k hyparameters

#25 JeffC0628 closed 6 months ago
0
Use with a fine-tuned model

#24 Ar770 opened 7 months ago
0
JAX-models

#23 WhyAreYouJay opened 7 months ago
0
fix triton install issue based on whisper updates

#22 shawnCaza opened 7 months ago
0
Support for whisper-large-v3

#21 spaghettiSystems opened 7 months ago
1
Still requests from url when models have been downloaded manually.

#20 ndz2011 closed 8 months ago
2
RuntimeError: torch.cat(): expected a non-empty list of Tensors

#19 herbiel opened 8 months ago
0
invalid for input of size 95904000 ?

#18 herbiel closed 8 months ago
22
how to inference with batch?

#17 dinoSpeech opened 8 months ago
1
'Whisper' object has no attribute 'transcribe_audio'

#16 herbiel opened 9 months ago
8
How to run eval for the Other dataset UrbanSound, FreeSound, etc.,

#15 asifsha11 opened 9 months ago
1
can support real time asr?

#14 herbiel closed 9 months ago
4
miss the file of balance sample

#13 JeffC0628 closed 9 months ago
10
writing json file error

#12 ilanit1997 opened 10 months ago
2
How to output Srt format

#11 lsdlh opened 11 months ago
0
Occasional IndexError on empty segments

#10 noeliadlc opened 11 months ago
1
Whisper C++ integration

#9 gasparitiago opened 11 months ago
1
Update transcribe.py

#8 shehanmunasinghe opened 1 year ago
0
whisper-at does not recognize laughter

#7 Shivansh-yadav13 closed 11 months ago
5
Missing train & eval data json file

#6 Stanwang1210 opened 1 year ago
3
How to Use Temporal Pooling Layer?

#5 Yunlei-AI opened 1 year ago
3
Exception using word_timestamps=True in model.transcribe

#4 tallzilla opened 1 year ago
5
downloading forms a bad path

#3 raresv closed 1 year ago
5
Can't install on Apple Silicon due to triton dependency

#2 whicks1 opened 1 year ago
8
Possible use faster-whisper (https://github.com/guillaumekln/faster-whisper) backend?

#1 tensorboy opened 1 year ago
5