Remsky commited on
Commit
72f4e7a
·
1 Parent(s): 0a639cb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -28
README.md CHANGED
@@ -1,14 +1,16 @@
1
  ---
2
  title: Kokoro TTS Zero
3
  emoji: 📊
4
- colorFrom: blue
5
- colorTo: gray
6
  sdk: gradio
7
  sdk_version: 5.9.1
8
  app_file: app.py
9
- pinned: false
10
  license: apache-2.0
11
  short_description: A100 GPU Accelerated Inference applied to Kokoro-82M TTS
 
 
12
  ---
13
 
14
  # Kokoro TTS Demo Space
@@ -24,16 +26,10 @@ This Space provides a Gradio interface for the Kokoro TTS model, allowing users
24
 
25
  ## Technical Details
26
 
27
- - Uses Zero GPU for efficient GPU resource management
28
  - Dynamically loads required modules from hexgrad/Kokoro-82M repository
29
- - Automatically downloads model and voice files from Hugging Face Hub
30
- - Implements proper GPU memory handling
31
- - Includes caching in /data/.huggingface for faster restarts
32
 
33
  ## Dependencies
34
-
35
- The Space uses modules from two repositories:
36
- - remsky/Kokoro-FastAPI: This repository (UI and Zero GPU implementation)
37
  - hexgrad/Kokoro-82M: Original model repository (core TTS functionality)
38
 
39
  All dependencies are automatically handled:
@@ -46,27 +42,22 @@ All dependencies are automatically handled:
46
  - Python 3.10.13
47
  - PyTorch 2.2.2
48
  - Gradio 5.9.1
49
- - Zero GPU compatible
50
 
51
  ## Available Voices
52
 
53
- Adult Female voices:
54
- - af: Confident, Friendly
55
- - af_sky: You know and Love her
56
- - af_bella: Warm and Self-Assured
57
- - af_nicole: Whispered, ASMR
58
- - af_sarah: Bright and Professional
59
- - bf_emma: Pensive and Confident, British
60
- - bf_isabella: Young Professional, British
61
 
62
- Adult Male voices:
63
- - am_adam: Deep Narrative Voice
64
- - am_michael: Trustworthy and Thoughtful
65
- - bm_george: Distinguished older voice, British
66
- - bm_lewis: Assured and Raspy, British
67
 
68
  ## Notes
69
-
70
- - First generation may take longer due to model initialization
71
- - GPU is allocated only during speech generation
72
- - Model and voices are cached in /data/.huggingface for faster subsequent runs
 
1
  ---
2
  title: Kokoro TTS Zero
3
  emoji: 📊
4
+ colorFrom: gray
5
+ colorTo: purple
6
  sdk: gradio
7
  sdk_version: 5.9.1
8
  app_file: app.py
9
+ pinned: true
10
  license: apache-2.0
11
  short_description: A100 GPU Accelerated Inference applied to Kokoro-82M TTS
12
+ models:
13
+ - hexgrad/Kokoro-82M
14
  ---
15
 
16
  # Kokoro TTS Demo Space
 
26
 
27
  ## Technical Details
28
 
29
+ - Zero GPU for efficient GPU resource management
30
  - Dynamically loads required modules from hexgrad/Kokoro-82M repository
 
 
 
31
 
32
  ## Dependencies
 
 
 
33
  - hexgrad/Kokoro-82M: Original model repository (core TTS functionality)
34
 
35
  All dependencies are automatically handled:
 
42
  - Python 3.10.13
43
  - PyTorch 2.2.2
44
  - Gradio 5.9.1
45
+ - A100 Zero GPU Enabled
46
 
47
  ## Available Voices
48
 
49
+ af: Default
50
+ af_sky: Classic
51
+ af_bella: Warm
52
+ af_nicole: Soothing
53
+ af_sarah: Polished
54
+ bf_emma: Contemplative
55
+ bf_isabella: Poised
 
56
 
57
+ am_adam: Resonant
58
+ am_michael: Sincere
59
+ bm_george: Distinguished
60
+ bm_lewis: Gravelly
 
61
 
62
  ## Notes
63
+ - Model Warm-Up takes some time, it shines at longer lengths.