Text-to-Speech
F5-TTS
SWivid commited on
Commit
8d46f84
1 Parent(s): 67a123c

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +27 -0
README.md ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ pipeline_tag: text-to-speech
4
+ library_name: e2-tts
5
+ datasets:
6
+ - amphion/Emilia-Dataset
7
+ ---
8
+ ### 2024/10/14. We change the License of this ckpt repo to CC-BY-NC-4.0 following the used training set Emilia, which is an in-the-wild dataset. Sorry for any inconvenience this may cause. Our codebase remains under the MIT license.
9
+
10
+ Download [F5-TTS](https://huggingface.co/SWivid/F5-TTS/tree/main/F5TTS_Base) or [E2 TTS](https://huggingface.co/SWivid/E2-TTS/tree/main/E2TTS_Base) and place under ckpts/
11
+ ```
12
+ ckpts/
13
+ E2TTS_Base/
14
+ model_1200000.pt
15
+ F5TTS_Base/
16
+ model_1200000.pt
17
+ ```
18
+ Inference with .safetensors option
19
+ ```
20
+ ckpts/
21
+ E2TTS_Base/
22
+ model_1200000.safetensors
23
+ F5TTS_Base/
24
+ model_1200000.safetensors
25
+ ```
26
+ Github: https://github.com/SWivid/F5-TTS
27
+ Paper: [E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS](https://huggingface.co/papers/2406.18009)