---
title: glm-4-voice-tokenizer
canonical_url: "https://www.modelscope.cn/models/ZhipuAI/glm-4-voice-tokenizer"
md_url: "https://www.modelscope.cn/models/ZhipuAI/glm-4-voice-tokenizer.md"
repository: ZhipuAI/glm-4-voice-tokenizer
last_updated: 2024-10-25
pipeline_tag: auto-speech-recognition
tasks:
  - auto-speech-recognition
model_type:
  - whisper
architectures:
  - WhisperVQEncoder
parameters: 364.6M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - Pytorch
downloads: 738800
stars: 34
---

# glm-4-voice-tokenizer

> glm-4-voice-tokenizer - ZhipuAI 在 ModelScope 开源的模型。GLM-4-Voice-Tokenizer

- **Repository**: ZhipuAI/glm-4-voice-tokenizer
- **Tasks**: auto-speech-recognition
- **Parameters**: 364.6M
- **Downloads**: 738800
- **Stars**: 34
- **Last updated**: 2024-10-25

Source: https://www.modelscope.cn/models/ZhipuAI/glm-4-voice-tokenizer

---

# GLM-4-Voice-Tokenizer

GLM-4-Voice 是智谱 AI 推出的端到端语音模型。GLM-4-Voice 能够直接理解和生成中英文语音，进行实时语音对话，并且能够根据用户的指令改变语音的情感、语调、语速、方言等属性。

GLM-4-Voice is an end-to-end voice model launched by Zhipu AI. GLM-4-Voice can directly understand and generate Chinese and English speech, engage in real-time voice conversations, and change attributes such as emotion, intonation, speech rate, and dialect based on user instructions.

本仓库是 GLM-4-Voice 的 speech tokenizer 部分。通过在 [Whisper](https://github.com/openai/whisper) 的 encoder 部分增加 vector quantization 进行训练，将连续的语音输入转化为离散的 token。每秒音频转化为 12.5 个离散 token。

The repo provides the speech tokenzier of GLM-4-Voice, which is trained by adding vector quantization to the encoder part of [Whisper](https://github.com/openai/whisper) and converts continuous speech input into discrete tokens. Each second of audio is converted into 12.5 discrete tokens.

更多信息请参考我们的仓库 [GLM-4-Voice](https://github.com/THUDM/GLM-4-Voice).

For more information please refer to our repo [GLM-4-Voice](https://github.com/THUDM/GLM-4-Voice).