sachin
commited on
Commit
·
06a5720
1
Parent(s):
87516e4
Init slabstech
Browse files
README.md
CHANGED
@@ -7,4 +7,69 @@ sdk: docker
|
|
7 |
pinned: false
|
8 |
---
|
9 |
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
pinned: false
|
8 |
---
|
9 |
|
10 |
+
# S Labs Solutions
|
11 |
+
|
12 |
+
### Active Projects
|
13 |
+
|
14 |
+
|
15 |
+
--
|
16 |
+
|
17 |
+
# Dhwani - Your Kannada Speaking Voice Buddy
|
18 |
+
|
19 |
+
## Overview
|
20 |
+
|
21 |
+
Dhwani is a self-hosted GenAI platform designed to provide voice mode interaction for Kannada and other Indian languages.
|
22 |
+
|
23 |
+
## Research Goals
|
24 |
+
|
25 |
+
- Measure and improve the Time to First Token Generation (TTFTG) for model architectures in ASR, Translation, and TTS systems.
|
26 |
+
- Develop and enhance a Kannada voice model that meets industry standards set by OpenAI, Google, ElevenLabs, xAI
|
27 |
+
- Create robust voice solutions for Indian languages, with a specific emphasis on Kannada.
|
28 |
+
|
29 |
+
|
30 |
+
## Project Video
|
31 |
+
|
32 |
+
|
33 |
+
- Dhwani - Intoduction to Project
|
34 |
+
[](https://youtu.be/kqZZZjbeNVk)
|
35 |
+
|
36 |
+
|
37 |
+
|
38 |
+
- [Pitch Deck](https://docs.google.com/presentation/d/e/2PACX-1vQxLtbL_kXOqHgAHqcFTg8hDP7Dw3lt64U336J0f9CgYQPKDJVqONd3F4Js1XiCvk_LDpbijshQ5mM6/pub?start=false&loop=false&delayms=3000)
|
39 |
+
|
40 |
+
|
41 |
+
## Models and Tools
|
42 |
+
|
43 |
+
The project utilizes the following open-source tools:
|
44 |
+
|
45 |
+
| Open-Source Tool | Source Repository |
|
46 |
+
|---------------------------------------|-------------------------------------------------------------|
|
47 |
+
| Automatic Speech Recognition : ASR | [ASR Indic Server](https://github.com/slabstech/asr-indic-server) |
|
48 |
+
| Text to Speech : TTS | [TTS Indic Server](https://github.com/slabstech/tts-indic-server) |
|
49 |
+
| Translation | [Indic Translate Server](https://github.com/slabstech/indic-translate-server) |
|
50 |
+
| Document Parser | [Indic Document Server](https://github.com/slabstech/docs-indic-server) |
|
51 |
+
| Dhwani Server | [Dhwani Server](https://github.com/slabstech/dhwani-server) |
|
52 |
+
| Dhwani Android | [Android](https://github.com/slabstech/dhwani-android) |
|
53 |
+
| Large Language Model | [LLM Indic Server](https://github.com/slabstech/llm-indic-server_cpu) |
|
54 |
+
|
55 |
+
|
56 |
+
## Features
|
57 |
+
|
58 |
+
| Feature | Description | Components |
|
59 |
+
|------------------------------|-----------------------------------------------------------------------------|-----------|
|
60 |
+
| Kannada Voice AI | Provides answers to voice queries using a LLM | LLM |
|
61 |
+
| Text Query | Allows querying text data for specific information. | LLM |
|
62 |
+
| Voice to Text Translation | Converts spoken language to text and translates it. | ASR, Translation |
|
63 |
+
| PDF Translate | Translates content from PDF documents. |
|
64 |
+
| Text to Speech | Generates speech from text. | TTS |
|
65 |
+
| Voice to Voice Translation | Converts spoken language to text, translates it, and then generates speech. | ASR, Translation, TTS|
|
66 |
+
| Answer Engine with Translate| Provides answers to queries with translation capabilities. | ASR, LLM, Translation, TTS|
|
67 |
+
|
68 |
+
|
69 |
+
## Contact
|
70 |
+
- For any questions or issues, please open an issue on GitHub or contact us via email.
|
71 |
+
- For collaborations
|
72 |
+
- Join the discord group - [invite link](https://discord.gg/WZMCerEZ2P)
|
73 |
+
- For business queries, Email : info (at) slabstech (dot) com
|
74 |
+
|
75 |
+
|