inference speed at the top

PolyAI-LDN · Jan 4, 2024 · 3520173 · 3520173
1 parent 8589a7a
commit 3520173
Showing 1 changed file with 8 additions and 7 deletions.
diff --git a/docs/index.md b/docs/index.md
@@ -4,6 +4,14 @@
  - [Code](https://github.com/PolyAI-LDN/pheme)
  - [Paper](...)
 
+### Inference speed(RTFs, lower is better) on a single A100 GPU, for short and long sentances
+
+| Model              | *short*   | *long*    |
+| ------------------ | --------- | --------- |
+| MQTTS (100M)       | 1.930     | 1.842     |
+| PHEME-SMALL (100M) | **0.133** | **0.133** |
+| PHEME-LARGE (300M) | 0.143     | 0.143     |
+
 ### Artificial Voice TTS Examples 
 
 
@@ -31,11 +39,4 @@
 
 
 
-### Inference speed(RTFs, lower is better) on a single A100 GPU, for short and long sentances
-
-| Model              | *short*   | *long*    |
-| ------------------ | --------- | --------- |
-| MQTTS (100M)       | 1.930     | 1.842     |
-| PHEME-SMALL (100M) | **0.133** | **0.133** |
-| PHEME-LARGE (300M) | 0.143     | 0.143     |