# Voice to text with Mozilla Deepspeech

One of the primary function of computers is to parse data.
Some data is easier to parse than other data, and voice input continues to be a work in progress.
There have been many improvements in the area in recent years, though, and one of them is in the form of DeepSpeech, a project by Mozilla, the foundation that maintains the Firefox web browser.
DeepSpeech is a voice-to-text command and library, making it useful to both users who need to transform voice input into text and to developers who want to provide voice input for their applications.

## Install

DeepSpeech is open source, released under the Mozilla Public License (MPL).
You can download the source code from its [Github](https://github.com/mozilla/DeepSpeech) page.

To install, first create a virtual environment for Python:

```bash
$ python3 -m pip install deepspeech --user
```

DeepSpeech relies on machine learning.
You can train it yourself, but when you're just starting out it's easiest to just download pre-trained model files.

```bash
$ mkdir DeepSpeech
$ cd Deepspeech
$ curl -LO \
https://github.com/mozilla/DeepSpeech/releases/download/vX.Y.Z/deepspeech-X.Y.Z-models.pbmm
$ curl -LO \
https://github.com/mozilla/DeepSpeech/releases/download/vX.Y.Z/deepspeech-X.Y.Z-models.scorer
```

## Applications for users

With DeepSpeech, you can transcribe recordings of speech to written text.
You get the best results from speech cleanly recorded under optimal conditions, although in a pinch you can try any recording and you'll probably get something you can use as a starting point for manual transcription.

For test purposes, you might record an audio file containing the simple phrase "This is a test. Hello world, this is a test."
Save the audio as a `.wav` file called `hello-test.wav`.

In your DeepSpeech folder, launch a transcription by providing the model file, the scorer file, and your audio:

```bash
$ deepspeech --model deepspeech*pbmm \
--scorer deepspeech*scorer \
--audio hello-test.wav
```

Output is provided to the standard out (your terminal):

```text
this is a test hello world this is a test
```

You can get output in JSON format by using the `--json` option:

```bash
$ deepspeech --model deepspeech*pbmm \
-- json
--scorer deepspeech*scorer \
--audio hello-test.wav
```

This renders each word along with a timestamp:

```json
{
  "transcripts": [
    {
      "confidence": -42.7990608215332,
      "words": [
        {
          "word": "this",
          "start_time": 2.54,
          "duration": 0.12
        },
        {
          "word": "is",
          "start_time": 2.74,
          "duration": 0.1
        },
        {
          "word": "a",
          "start_time": 2.94,
          "duration": 0.04
        },
        {
          "word": "test",
          "start_time": 3.06,
          "duration": 0.74
        },
[...]
```

## Developers

DeepSpeech isn't just a command to transcribe pre-recorded audio.
It can also be used to process audio streams in realtime.
The Github repository [DeepSpeech-examples](https://github.com/mozilla/DeepSpeech-examples) is full of Javascript, Python, C#, and Java for Android.

Most of the hard work is already done, so integrating DeepSpeech usually is just a matter of referencing the DeepSpeech library, and knowing how to obtain audio from the host device (which is generally done through the `/dev` filesystem on Linux, or an SDK on Android and other platforms.)

## Speech recognition

As a developer, enabling speech recognition for your application isn't just a fun trick, but an important accessibility feature that makes your appication easier to use by people with mobility issues, low vision, and chronic multi-taskers who like to keep their hands full.
As a user, DeepSpeech is a useful transcription tool that can convert audio files into text.
Recardless of your use case, try DeepSpeech and see what it can do for you.