---
license: other
license_name: glm-4-voice
license_link: https://github.com/THUDM/GLM-4-Voice/blob/main/MODEL_LICENSE
tags:
  - speech-to-speech
  - audio
  - emotion
  - kimi-audio
  - glm-4-voice
---

# glm-4-voice-decoder-emo-ft

> Built with glm-4.

Fine-tuned [GLM-4-Voice](https://github.com/THUDM/GLM-4-Voice) decoder
weights for **emotion-preserving Chinese ↔ English speech-to-speech
translation**, used together with the
[Kimi-Audio Emotion-Aware S2ST](https://github.com/<YOUR_GH_USER>/kimi-audio-release)
training / inference pipeline.

## Files

| File | Size | Role |
|---|---|---|
| `epoch500_emoft.pt` | ~425 MB | Fine-tuned flow checkpoint (emotion-preserving) |
| `hift.pt` | ~79 MB | HiFT vocoder checkpoint |

## Usage

```bash
git clone https://github.com/<YOUR_GH_USER>/kimi-audio-release
cd kimi-audio-release
./scripts/download_weights.sh
# the two files will be placed under glm_4_voice_decoder/

'EOF'