DanSpeech demo.
This is a demo that demonstrates some of the functionality of the danspeech python package.
Note that the demo includes some functionality of Danspeech that requires PyAudio and ctcdecoce.
For the best possible experience, please download and install these libraries as well!
Else, the following will enable danspeech.
$ pip install danspeech
$ pip install django
$ git clone https://github.com/danspeech/danspeechdemo.git
$ cd danspeechdemo
$ pip install .
Now, execute a script or run from terminal as below:
$ python
>>> import danspeechdemo
>>> danspeechdemo.run_server()
The demo will then be live at http://127.0.0.1:8000.
Features not working correctly:
- Streaming
- Folketinget example
These features will be added as soon as possible.
Main authors:
- Martin Nielsen ([email protected])
- Rasmus Arpe Fogh Jensen ([email protected])
This project is supported by Innovation Foundation Denmark through the projects DABAI and ATEL
Other acknowledgements:
- We've trained the models based on the code from https://github.com/SeanNaren/deepspeech.pytorch.
- The audio handling and recognizing flow is based on https://github.com/Uberi/speech_recognition.
- Handling of the pretrained models is based on keras.
- We've trained all models with the aid of DTU using data from Sprakbanken (NST).