Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,13 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
This is a streamlined interface version of [WavTokenizer-large-speech-75token](https://huggingface.co/novateur/WavTokenizer-large-speech-75token/tree/main), providing a clean, efficient way to interact with the model through separate encoder and decoder components.
|
| 6 |
+
|
| 7 |
+
- Reduced model size from 1.75GB to ~330MB by keeping only necessary components for inference
|
| 8 |
+
- Split interface (82MB encoder, 248MB decoder)
|
| 9 |
+
- Simplified integration with just [one .py](https://github.com/edwko/OuteTTS) file
|
| 10 |
+
|
| 11 |
+
The model is split into:
|
| 12 |
+
- `encoder/`: Handles audio encoding
|
| 13 |
+
- `decoder/`: Handles decoding and synthesis
|