# Tasks

---
## Dataset collection
[Mozilla common voice dataset](https://commonvoice.mozilla.org/en/datasets)

---

## API tests
#### Expected time 1 week

- [ ] Finish

### [Python Speech Recognition api](https://pypi.org/project/SpeechRecognition/)

[How to use it](https://realpython.com/python-speech-recognition/)

[Test script](https://colab.research.google.com/drive/1sqkd3S0eMWf0CW1F2D6hUye-b5Y7DN5s?usp=sharing)

[Fix couldn't install PyAudio on Windows10](https://stackoverflow.com/a/55630212)

[Fix couldn't install PyAudio on Ubuntu 18.04](https://ourcodeworld.com/articles/read/974/how-to-solve-installation-error-of-pyaudio-in-ubuntu-18-04-fatal-error-portaudio-h-file-not-found)

[Python socket](https://realpython.com/python-sockets/)

[Python threading](https://realpython.com/python-pyqt-qthread/?utm_source=pocket_mylist)

[GUI Application](https://github.com/hohohome/speech-recognition)

## Pretrained models
#### Expected time 1 week

- [ ] Finish

### [Mozilla DeepSpeech](https://github.com/mozilla/DeepSpeech)

[Documentation](https://deepspeech.readthedocs.io/en/r0.9/?badge=latest)

[DeepSpeech discourse forum](https://discourse.mozilla.org/c/deepspeech/247)
### [Google Dialogflow](https://cloud.google.com/dialogflow/docs/support/troubleshooting?agent=any&category=any)

## Training for Speech Datasets
#### Expected time 1 week

- [ ] Finish

---

## Others
[Line Engineering speech](https://engineering.linecorp.com/zh-hant/blog/speech-technology-0207/)
[Sequence Modeling With CTC](https://distill.pub/2017/ctc/)