Overview
Friday is an AI assistant inspired from Tony Stark's replacement of Vision. Friday uses vosk model for speech recognition and a custom Natural Language Processing Server that runs in the local host, to identify commands.
Friday can also speak, which is done using a custom library written in rust (using tts_rust crate), making use of GTTS (Google Text to Speech) client. The rust lib is integrated into python with maturin.
Table of Contents
- Mechanism
- Requirements (
Manadatory) - Installation
- Usage
Mechanism
-
Speech to Text
-
Fridayneeds avosk modelto recognize speech and convert it to text.Fridayparticularly uses Indian english version of the model. Find it here along with several other versions ofvosk. -
The output from
voskis processed by a custom NLP server running in the local host, that returns the properly processed command back toFriday. This NLP server has been made using rasa platform. -
Both
vosk modelandNLP serverare part ofFriday's "Brain" and are a vital part ofFriday's response.
-
-
Text to Speech
-
Friday's speaking abilities are powered byGoogle Text To Speechclient, which was used to writeFriday's TTS library in rust (for speed). -
Apart from that,
Fridayuses threads to speak, which further enhancesFriday's voice control.
-
-
Overall Integration
Friday's overall integration is a result of simultaneous working of several components altogether.
Requirements
-
Mandatorycondacondamust be installed in the system and enabled. -
Mandatorypython v3.12rasauses python v3.9 and it will be installed in a separate conda env automatically byFriday -
Mandatorymaturincan be installed using
$ pip install maturin -
ffmpeg
ffmpegis not a mandatory requirement but ifFridayencounters some errors related to it, download it.
Installation
To install Friday, clone this repository.
git clone https://github.com/d33pster/Friday.git
then, move into the directory with cd.
cd Friday
then, install it using pip.
maturinneeds to be installed before this step.
pip install .
Usage
To use Friday, open two terminals.
in terminal 1
friday server
and wait for it show, rasa server is up and running!
after that, in terminal 2
friday
After
Fridayis online, just call "Friday!" to wakeFridayup. and then a command.
Metadata
Release files for friday-d33pster 0.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| friday_d33pster-0.2.tar.gz | 28.8 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| friday_d33pster-0.2-cp312-cp312-macosx_11_0_arm64.whl | CPython 3.12 | CPython 3.12 | macOS 11.0+ ARM64 | Details |
Total release size: 1.1 MB
Release files / friday_d33pster-0.2.tar.gz
| Download URL | friday_d33pster-0.2.tar.gz |
|---|---|
| Size | 28.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3bb66b5f8e0b5d8a77069ed744acddc4f560b3deffc22d05d4fadb13cd0fb89b
|
|
BLAKE2b-256 checksum How to use checksums |
48a493acda59084b45e24954cd0e9a0b3a87f4f1995bfb5213512a78b2241658
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.0 CPython/3.12.3
|
Release files / friday_d33pster-0.2-cp312-cp312-macosx_11_0_arm64.whl
| Download URL | friday_d33pster-0.2-cp312-cp312-macosx_11_0_arm64.whl |
|---|---|
| Size | 1.1 MB |
| Tags | CPython 3.12 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
954f9dfd2b5ca555ca3872f7797d1bd24f8138987d1c79b2db9f2333ef12e012
|
|
BLAKE2b-256 checksum How to use checksums |
1408a922cff332d4a31cbb4f44502e555b92ef9ba80d981452d39214c9155ec5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.0 CPython/3.12.3
|
Security for friday-d33pster 0.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.