Comments (3)
Hi Aki58, I think the problem is in the dimensionality of the data, it sometimes happens that the generated spectogram images are a bit shorter than supposed. Check this issue that I had and see if you can get something with the Spectrogram generator's small x parameter (the total width of the spectrogram image). Basically what I think is happening to you is that you're trying to predict on an audio file which is converted to a spectrogram but not to the expected dimension and therefore the prediction fails.
I unfortunately hadn't had time to make a pull request to this repo, but this change has been applied in the version that I forked
from crnn-lid.
Hi ibro45,
Thanks for your help, I also thought that this might be the case as I was providing 2-3 seconds of the audio file to predict. I will make the appropriate changes as suggested by you.
from crnn-lid.
Hi @ibro45 ,
Your decision didn't work for me, still getting the same error on some files, some work out fine with both yours and the original code.
from crnn-lid.
Related Issues (20)
- Train issue. HOT 2
- Training steps. HOT 9
- train.py error
- Train error with finetune_crnn model. HOT 4
- voxforge download script is corrupted on OSX Catalina
- Failing to import model package HOT 2
- Fails to load weight file HOT 4
- value of nb_val_samples is none: validation_data_generator.get_num_files() returns 0 HOT 1
- Size issue with convolutions HOT 2
- Training comes to a stand-still
- Predict new audio - audio is not found HOT 15
- Early Stopping occurs during training HOT 11
- Unable to open model HOT 5
- on the usage of an additional labels HOT 1
- "SpectrogramGenerator Exception: [Errno 2] No such file or directory: 'tmp_images/tmp_91484.png' audio_segment/malayalam" HOT 4
- Delete this issue
- downloading dataset error
- SpectrogramGenerator Exception: [Errno 2] No such file or directory: HOT 3
- Changing to shorter segments HOT 1
- Model Overfitting HOT 2
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 crnn-lid.