rasenganai
commited on
Commit
•
edaade8
1
Parent(s):
7ad668d
Update README.md
Browse files
README.md
CHANGED
@@ -1 +1,114 @@
|
|
1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<div align="center">
|
2 |
+
|
3 |
+
<h1>MahaTTS: An Open-Source Large Speech Generation Model in the making</h1>
|
4 |
+
a Dubverse Black initiative <br> <br>
|
5 |
+
|
6 |
+
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1-eOQqznKWwAfMdusJ_LDtDhjIyAlSMrG?usp=sharing)
|
7 |
+
|
8 |
+
</div>
|
9 |
+
|
10 |
+
------
|
11 |
+
|
12 |
+
## Description
|
13 |
+
MahaTTS (Maha means 'Great' in sanskrit), is a speech generation model which is inspired from tortoise-tts, except it uses seamless M4t wav2vec2 to extract semantic tokens.
|
14 |
+
Since seamless M4t wav2vec2 is trained on multilingual data, it makes this model easier to scale on multilingual data.
|
15 |
+
|
16 |
+
<img width="993" alt="Screenshot 2023-11-19 at 11 53 52 PM" src="https://github.com/dubverse-ai/MahaTTS/assets/32906806/7429d3b6-3f19-4bd8-9005-ff9e16a698f8">
|
17 |
+
|
18 |
+
|
19 |
+
## Features
|
20 |
+
1. Multilinguality
|
21 |
+
2. Realistic Prosody and intonation
|
22 |
+
3. Multi-voice capabilities
|
23 |
+
|
24 |
+
## Current Progress
|
25 |
+
Trained on 200 hours of LibriTTS model -> 'Smolie'
|
26 |
+
|
27 |
+
## Installation
|
28 |
+
```bash
|
29 |
+
pip install git+https://github.com/dubverse-ai/MahaTTS.git
|
30 |
+
```
|
31 |
+
|
32 |
+
```bash
|
33 |
+
pip install maha-tts
|
34 |
+
```
|
35 |
+
## Roadmap
|
36 |
+
- [x] Smolie - eng
|
37 |
+
- [ ] Smolie - indic
|
38 |
+
- [ ] Optimizations for inference
|
39 |
+
|
40 |
+
## Some Generated Samples
|
41 |
+
text:
|
42 |
+
0 -> "I seriously laughed so much hahahaha (seals with headphones...) and appreciate both the interviewer and the subject. Major respect for two extraordinary humans - and in this time of gratefulness, I'm thankful for you both and this forum!"
|
43 |
+
|
44 |
+
1 -> "I freakin love how Elon came to life the moment they started talking about gaming and specifically diablo, you can tell that he didn't want that part of the discussion to end, while Lex to move on to the next subject! Once a true gamer, always a true gamer!"
|
45 |
+
|
46 |
+
2 -> "hello there! how are you?" (This one didn't work well, M1 model hallucinated)
|
47 |
+
|
48 |
+
3 -> "Who doesn't love a good scary story, something to send a chill across your skin in the middle of summer's heat or really, any other time? And this year, we're celebrating the two hundredth birthday of one of the most famous scary stories of all time: Frankenstein."
|
49 |
+
|
50 |
+
|
51 |
+
|
52 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/66fc7a08-3e8a-4d63-a3fa-88bc705a172a
|
53 |
+
|
54 |
+
|
55 |
+
|
56 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/5acf5a4b-aeb8-4f14-94fe-45811868a886
|
57 |
+
|
58 |
+
|
59 |
+
|
60 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/0af2ce6e-4172-4aac-9322-4fd545f1d4ac
|
61 |
+
|
62 |
+
|
63 |
+
|
64 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/2d5b0335-d1fc-473a-aea8-c5bb6afbce27
|
65 |
+
|
66 |
+
|
67 |
+
|
68 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/a63ba39f-a261-4fe6-8d06-a172a993acc1
|
69 |
+
|
70 |
+
|
71 |
+
|
72 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/4355f633-9b27-4290-a284-96d650f5f4b8
|
73 |
+
|
74 |
+
|
75 |
+
|
76 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/7c93d81e-02bc-4819-a97b-d48e39ec5689
|
77 |
+
|
78 |
+
|
79 |
+
|
80 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/63456535-0b38-429a-a8a0-686cfb6a92c5
|
81 |
+
|
82 |
+
|
83 |
+
|
84 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/960aa78c-888f-4f0b-a380-145a87f65a99
|
85 |
+
|
86 |
+
|
87 |
+
|
88 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/5027f0eb-3601-468b-9dda-6b436b774741
|
89 |
+
|
90 |
+
|
91 |
+
|
92 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/266285e0-a8f3-4784-81dc-f98b0a9c9373
|
93 |
+
|
94 |
+
|
95 |
+
|
96 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/68ba18d6-430b-41e7-84e5-e15990064836
|
97 |
+
|
98 |
+
|
99 |
+
|
100 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/0f7321a7-efb1-407c-8b8c-69e812865739
|
101 |
+
|
102 |
+
|
103 |
+
|
104 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/dcedffe6-d81b-4eff-95c0-cbd00279fdb7
|
105 |
+
|
106 |
+
|
107 |
+
|
108 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/8050db3e-7acb-44be-a039-7e0b9e6a9905
|
109 |
+
|
110 |
+
|
111 |
+
|
112 |
+
https://github.com/dubverse-ai/MahaTTS/assets/32906806/6486af1c-2e14-420b-8419-bf5e01fe49a5
|
113 |
+
|
114 |
+
|