msalhab96 / speeq Goto Github PK
View Code? Open in Web Editor NEWA framework for automatic speech recognition
Home Page: https://speeq.readthedocs.io/
License: MIT License
speeq's People
Contributors
Stargazers
Watchers
speeq's Issues
Adding librispeech recipe
Description
Adding script that does data re-structuring and formatting to be used and trained in the framework
Additional Information
No response
Adding Clipped ReLU after each conv layer in DeepSpeech2
What happened?
No response
What the code you used and failed?
No response
Version
No response
What python version do you use?
No response
What operating system are you running?
No response
[FEAT]: Supporting data shuffling and data sorting in the data loaders
Description
Currently the data is not sorted neither get shuffled during training
Additional Information
No response
Enhance CSVDataset class to have ',' as default sep
Description
Enhance CSVDataset class to have ',' as default sep.
Before the enhancment:
from speeq.data.loaders import CSVDataset
file = CSVDataset(data_path="test.csv", sep=',')After the enhancement:
from speeq.data.loaders import CSVDataset
file = CSVDataset(data_path="test.csv")Additional Information
No response
First item attention
What happened?
The current RNN based decoder with attention rely on the the last hidden state when it comes to the first prediction or injecting the SOS token, this should be resolved
What the code you used and failed?
N/AVersion
0.0.0
What python version do you use?
No response
What operating system are you running?
No response
Supporting word tokenizer
Description
Currently, the only tokenizer supported is a character based tokenizer, it would be good to add white space/word tokenizer
Additional Information
No response
Integrating the augmenters with the dataset
What happened?
currently, there's no way to integrate or use any augmentation implemented with the data pipeline
What the code you used and failed?
N/AVersion
0.0.0
What python version do you use?
No response
What operating system are you running?
No response
CTCModel can be instantiated
What happened?
An object from ctc.py::CTCModel can be instantiated, but the forward function raises an Error because self.encoder is not implemented.
Should be modified to private.
What the code you used and failed?
No response
Version
No response
What python version do you use?
No response
What operating system are you running?
No response
SpeechTransformer Decoder and Encoder missing LayerNorm
Line 359 in 6ef6da6
SpeechTransformer uses Transformer decoder, which does not match the decoder used in paper.
SpeechTransformerEncoder implementation missing LayerNorm
passing gradient clipping parameters to the trainers
What happened?
Currently when the trainer args get created the gradient clipping params get ignored!
What the code you used and failed?
No response
Version
No response
What python version do you use?
No response
What operating system are you running?
No response
Supporting Seq2Seq Builder
Description
Currently we support only Transducer builder and CTC builder only
Additional Information
No response
Adding a logging message when loading a model
Description
Currently, a pre-trained model get loaded silently, it would be better to add a log message indicates that the model is loadded
Additional Information
No response
Loading pre-trained model
Description
Currently, the optimizer parameters get loaded if a pre-trained model passed, it would be better if we Add an option to reset the optimizer learning rate when loading it
Additional Information
No response
setting min_loss in the trainer from pre-trained model
What happened?
When loading a pre-trained model to continue the training from the latest checkpoint the min_loss in the trainer gets assigned to inf it has to get the latest value reached from the history!
What the code you used and failed?
No response
Version
No response
What python version do you use?
No response
What operating system are you running?
No response
[FEAT]: Supporting gradient accumulation
Description
Adding gradient accumulation across training steps in the trainers
Additional Information
No response
Passing text_key and speech_key from the data config object
What happened?
the parameters text_key and speech_key in the SpeechTextDataset are not getting initialized from the data config object and they always take the default value
What the code you used and failed?
No response
Version
No response
What python version do you use?
No response
What operating system are you running?
No response
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.