deepspeech-server 0.4.0

server for mozilla deepspeech

# DeepSpeech Server

This is an http server that can be used to test the mozilla DeepSpeech project.
You need an environment with DeepSpeech and a model to run this server.

## Installation

You first need to install deepspeech. Depending on your system you can use the
CPU package:

pip3 install deepspeech

Or the GPU package:

pip3 install deepspeech-gpu

Then you can install the deepspeech server:

python3 setup.py install

The server is also available on pypi, so you can install it with pip:

pip3 install deepspeech-server

Note that python 3.5 is the minimum version required to run the server.

## Starting the server

deepspeech-server --config config.json

You can use deepspeech without training a model yourself. Pre-trained
models are provided by Mozilla in the release page of the project (See the
download section at the bottom):

https://github.com/mozilla/DeepSpeech/releases

### Server configuration

The configuration is done with a json file, provided with the "--config" argument.
Its structure is the following one:

{
"deepspeech": {
"model" :"model.pb",
"alphabet": "alphabet.txt",
"lm": "lm.binary",
"trie": "trie"
},
"server": {
"http": {
"request_max_size": 1048576
}
}
}

The configuration file contains several sections and sub-sections.

Section "deepspeech" contains configuration of the deepspeech engine:

__model__ is the protobuf model that was generated by deepspeech

__alphabet__ is the alphabet dictionary (as available in the "data" directory of
the DeepSpeech sources).

__lm__ is the language model.

__trie__ is the trie file.

Section "server" contains configuration of the access part, with on subsection per protocol:

http configuration:

__request_max_size__ (default value: 1048576, i.e. 1MiB) is the maximum payload
size allowed by the server. A received payload size above this threshold will
return a "413: Request Entity Too Large" error.

__host__ (default value: "0.0.0.0") is the listen address of the http server.

__port__ (default value: 8080) is the listening port of the http server.


## Using the server

Inference on the model is done via http post requests. For example with the
following curl command:

curl -X POST --data-binary @[myfile.wav] http://localhost:8000/stt