> For the complete documentation index, see [llms.txt](https://wenjia-s.gitbook.io/voice-to-text-project/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://wenjia-s.gitbook.io/voice-to-text-project/master.md).

# Pre-trained model

## To get started

First things first, I would like to create a virtual environment.

Here is my code:

```
# I have already made an environment in my anaconda, so I just need to open it.
$ cd /anaconda3/envs/deepspeech-venv
$ source ./lib/python3.6/venv/scripts/common/activate      
```

{% hint style="info" %}
 These codes vary from person to person.
{% endhint %}

Once you have created the environment. You can install the packages.

{% code title="" %}

```bash
$ pip install deepspeech-gpu
```

{% endcode %}

```bash
# Download pre-trained English model files
curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.7.3/deepspeech-0.7.3-models.pbmm
curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.7.3/deepspeech-0.7.3-models.scorer

# Download example audio files
curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.7.3/audio-0.7.3.tar.gz
tar xvf audio-0.7.3.tar.gz

# Transcribe an audio file
deepspeech --model deepspeech-0.7.3-models.pbmm --scorer deepspeech-0.7.3-models.scorer --audio audio/2830-3980-0043.wav
```

## Done!

![](/files/-M9DsOBhldLnuvv3n8J4)

![Yeah! These are what I get !](/files/-M9DsKnyVnCWbFuT3KE0)

## Exit

```bash
deactivate
```