Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,36 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
pipeline_tag: text-to-speech
|
| 6 |
+
---
|
| 7 |
+
# vui
|
| 8 |
+
|
| 9 |
+
Small Conversational speech models that can run on device
|
| 10 |
+
|
| 11 |
+
# Installation
|
| 12 |
+
|
| 13 |
+
```sh
|
| 14 |
+
uv pip install -e .
|
| 15 |
+
```
|
| 16 |
+
|
| 17 |
+
# Demo
|
| 18 |
+
|
| 19 |
+
```sh
|
| 20 |
+
python demo.py
|
| 21 |
+
````
|
| 22 |
+
|
| 23 |
+
# Models
|
| 24 |
+
|
| 25 |
+
Vui.BASE is base checkpoint trained on 40k hours of audio conversations
|
| 26 |
+
Vui.ABRAHAM is a single speaker model that can reply with context awareness.
|
| 27 |
+
Vui.COHOST is checkpoint with two speakers that can talk to each other.
|
| 28 |
+
|
| 29 |
+
# Voice Cloning
|
| 30 |
+
|
| 31 |
+
You can clone with the base model quite well but it's not perfect as hasn't seen that much audio / wasn't trained for long
|
| 32 |
+
|
| 33 |
+
# FAQ
|
| 34 |
+
|
| 35 |
+
1) Was developed with on two 4090's https://x.com/harrycblum/status/1752698806184063153
|
| 36 |
+
2) Hallucinations: yes the model does hallucinate, but this is the best I could do with limited resources! :(
|