GLM-4-Voice

text audio
Zhipu AI (Z.ai)
open-source
Zhipu AI's GLM-4-Voice (2024) is an open-source end-to-end speech model supporting Chinese and English.
Version: 4.0
Released: 1y 7d ago on 10/25/2024
Pricing:
  • details: free
Repository: GitHubRepo
License: MIT
Weights Available: Yes

Architecture

  • family: GLM
  • parameters: Unknown
  • training_data: Chinese and English speech and text
  • context_length: 131072
  • inference_type: local

Capabilities

  • speech recognition
  • speech generation
  • text-generation
  • translation

Languages Supported

enzh

Benchmarks

    Safety

    • content filtering
    • Designed for safe enterprise use

    Deployment

    • regions: self-hosted
    • hosting: local, Hugging Face Spaces
    • integrations: Text Generation WebUI

    Tags

    open-weightmultimodalspeech

    Join our community

    Connect with others, share experiences, and stay in the loop.

    LinkedIn

    Connect with us and explore career opportunities.

    Facebook

    Follow us for updates and community news.

    YouTube

    Watch our latest videos and tutorials.

    Twitter

    Follow our latest updates and announcements.

    Instagram

    Follow us for behind-the-scenes content.

    TikTok

    Follow us for short-form content and trends.