Are you referring to this section in README when say documentation ?
Again, it’s all documented: WAV 16 bits, text output.
When you say documented, are you referring to in README starting from
Getting the pre-trained model
I am referring to the very first part of the README https://github.com/mozilla/DeepSpeech/blob/master/README.md, just below the GIF:
Pre-built binaries that can be used for performing inference with a trained model can be installed with pip3. Proper setup using virtual environment is recommended and you can find that documented below.
A pre-trained English model is available for use, and can be downloaded using the instructions below.
Once everything is installed you can then use the deepspeech binary to do speech-to-text on short, approximately 5 second, audio files (currently only WAVE files with 16-bit, 16 kHz, mono are supported in the Python client):