Hugging Face's logo

zai-org
/
GLM-TTS

Text-to-Speech
GLM-TTS
Safetensors
Chinese
English
llm
tts
zero-shot
voice-cloning
reinforcement-learning
flow-matching
Model card Files
xet
 Community
12
ZHANGYUXUAN-zR commited on
Commit
891ebe8
·
verified ·
1 Parent(s): 0af6a30

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ pipeline_tag: text-to-speech
16
  # GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS
17
 
18
  <div align="center">
19
- <img src=https://raw.githubusercontent.com/zai-org/GLM-V/refs/heads/main/assets/images/logo.svg width="50%"/>
20
  </div>
21
 
22
  <p align="center">
@@ -50,7 +50,7 @@ GLM-TTS follows a two-stage design:
50
  2. **Stage 2 (Flow Matching):** A Flow model converts token sequences into high-quality mel-spectrograms, which are then turned into waveforms by a vocoder.
51
 
52
  <div align="center">
53
- <img src="https://raw.githubusercontent.com/zai-org/GLM-V/refs/heads/main/assets/images/architecture.png" width="60%" alt="GLM-TTS Architecture">
54
  </div>
55
 
56
  ### Reinforcement Learning Alignment
 
16
  # GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS
17
 
18
  <div align="center">
19
+ <img src=https://raw.githubusercontent.com/zai-org/GLM-TTS/refs/heads/main/assets/images/logo.svg width="50%"/>
20
  </div>
21
 
22
  <p align="center">
 
50
  2. **Stage 2 (Flow Matching):** A Flow model converts token sequences into high-quality mel-spectrograms, which are then turned into waveforms by a vocoder.
51
 
52
  <div align="center">
53
+ <img src="https://raw.githubusercontent.com/zai-org/GLM-TTS/refs/heads/main/assets/images/architecture.png" width="60%" alt="GLM-TTS Architecture">
54
  </div>
55
 
56
  ### Reinforcement Learning Alignment