`sh run_all.sh` prepares all ASR datasets (currently, only LibriSpeech available). After running, we have several summarization manifest files in json-format.
A manifest file summarizes a speech data set, with each line containing the meta data (i.e. audio filepath, transcript text, audio duration) of each audio file within the data set, in json format. Manifest file serves as an interface informing our system of where and what to read the speech samples.
`python compute_mean_std.py` computes mean and stdandard deviation for audio features, and save them to a file with a default name `./mean_std.npz`. This file will be used in both training and inferencing. The default feature of audio data is power spectrum, currently the mfcc feature is also supported. To train and infer based on mfcc feature, you can regenerate this file by
Usually, the parameters $\alpha$ and $\beta$ for the CTC [prefix beam search](https://arxiv.org/abs/1408.2873) decoder need to be tuned after retraining the acoustic model.