- Currently data is stored at
data/audioanddata/label. Maybe can follow LibriSpeech directory structure. AudioDataset- read data from directory and convert to spectogram. Variable length.dataloader_audio.collate_fnpad sequence. Yet to check compatiblity with nn.utils.TextProcessto clean text. Currently include to lower case, remove punctuations, numbers(including years) to words.
forked from nimotsu/speech-recognition
-
Notifications
You must be signed in to change notification settings - Fork 0
Sam-limyr/automatic-speech-recognition
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
A project to analyze the effectiveness of various neural networks on the topic of automatic speech recognition.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- Jupyter Notebook 98.2%
- Python 1.8%