Comments (7)
I just transferred the issue to pyannote.database
repo.
This seems to be an issue with a malformed or mislocated database.yml
file.
Can you please share
- the content of the PYANNOTE_DATABASE_CONFIG environment variable?
echo $PYANNOTE_DATABASE_CONFIG
- the content of
~/.pyannote/database.yml
or whichever file returned by the aboveecho
line.
from pyannote-database.
Thank you very much for your reply! What I got from echo $PYANNOTE_DATABASE_CONFIG
was:
/home/dawei/research-socialbit/pyannote-audio/tutorials/data_preparation/database.yml
And within the .yaml file I had something like:
Databases:
AMI: /home/dawei/research-socialbit/pyannote-audio/AMI_corpus/amicorpus/*/audio/{uri}.wav
MUSAN: /home/dawei/research-socialbit/pyannote-audio/AMI_corpus/amicorpus/AMI_corpus/musan/{uri}.wav
Protocols:
AMI:
SpeakerDiarization:
MixHeadset:
train:
annotation: /home/dawei/research-socialbit/pyannote-audio/tutorials/data_preparation/AMI/MixHeadset.train.rttm
annotated: /home/dawei/research-socialbit/pyannote-audio/tutorials/data_preparation/AMI/MixHeadset.train.uem
development:
annotation: /home/dawei/research-socialbit/pyannote-audio/tutorials/data_preparation/AMI/MixHeadset.development.rttm
annotated: /home/dawei/research-socialbit/pyannote-audio/tutorials/data_preparation/AMI/MixHeadset.development.uem
test:
annotation: /home/dawei/research-socialbit/pyannote-audio/tutorials/data_preparation/AMI/MixHeadset.test.rttm
annotated: /home/dawei/research-socialbit/pyannote-audio/tutorials/data_preparation/AMI/MixHeadset.test.uem
I also manually checked the return of the add_custom_protocols() function in the ~/pyannote/database/init.py. It seems that the return was none. I noticed that my issue could be fixed if I manually fed the path of the .yaml file to the add_custom_protocols() function. So I am not pretty sure why it could not detect my protocol automatically?
Sorry I opened another similar issue, it is now closed I think. Thanks for your time!
from pyannote-database.
Is your problem solved?
If not, what is the output of the following command?
PYANNOTE_DATABASE_CONFIG="/home/dawei/research-socialbit/pyannote-audio/tutorials/data_preparation/database.yml" python -c "from pyannote.database import get_databases; print(get_databases())"
from pyannote-database.
Hi,
I can only make it work when manually feeding the protocol path to the initial.py of the pyannote package. The output of the above command is ['MUSAN'].
I think it might be my system configuration issue. May I just make sure if it is the correct way to use my own protocol like this:
test_file = {'uri': 'sample', 'audio': '/../sample.wav',
'annotation': '/../protocol_of_sample_wav.rttm'}
Where 'sample' is the name of the tested wave file and 'protocol_of_sample_wav' is the protocol of the file.
Thank you very much for your time and patience!
from pyannote-database.
Hi @dawei-liang, is your problem solved?
from pyannote-database.
Closing stalled issue. Please ask me to re-open if needed.
from pyannote-database.
Hello, @hbredin i'm writing a code using pyannote in colab, but, when i use get_protocol() i recived the same msg, but my file is correct, and when i run the code that you cited above, its works: [AMI,MUSAN].
But, not work when i just use get_protocol()... The variable PYANNOTE_DATABASE_CONFIG persist in colab, but independent code not work. Can you help?
from pyannote-database.
Related Issues (20)
- Add support for Python 3.12
- No loader for file with '.rttm' suffix HOT 5
- problem with pyannote HOT 3
- Training the overlap detection : AttributeError: 'PosixPath' object has no attribute 'format' HOT 2
- pyannote-audio sad train fails HOT 3
- Wrapper around various audio dataset libraries HOT 1
- AttributeError: 'PosixPath' object has no attribute 'format' HOT 3
- Bug on database.yml HOT 1
- Error in dataloader : 'PosixPath' object has no attribute 'format' HOT 5
- Multiple preprocessor for same field HOT 5
- Training on Jamendo Corpus HOT 4
- Deprecated plugin system HOT 7
- AttributeError: 'NoneType' object has no attribute 'items' HOT 6
- Add support for SPKR-INFO lines in load_rttm HOT 3
- LABLoader import error HOT 1
- ImportError: cannot import name 'registry' from 'pyannote.database' HOT 3
- Faster RTTMLoader HOT 2
- Speaker tag across rttm files
- Cannot combine several protocols from different databases into one HOT 1
- `LABLoader` raise ValueError("`path` must contain the {uri} placeholder.") even if the placeholder is configured correctly HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pyannote-database.