Oriel — AI & technology worth noticing, every day.

inclusionAI/Ming-3.0-tts-0.5B

AI model · https://huggingface.co/inclusionAI/Ming-3.0-tts-0.5B

First seen by Oriel on .

AI summary

Ming-3.0-tts-0.5B is a 0.5B-parameter multilingual speech synthesis checkpoint built on Qwen2.5-0.5B, offering voice cloning, voice design, and fine-grained speech controls.

  • It supports Chinese, English, German, Spanish, French, Korean, Japanese, plus Sichuanese and Cantonese dialect control.
  • Capabilities include zero-shot voice cloning, natural-language voice design, emotion and delivery controls, and 14 inline tags for vocal events.
  • The checkpoint includes the backbone, DiT head, audio tokenizer, speaker encoder, and text tokenizer; inference requires the separate Ming-3.0-tts GitHub repository.
  • Reported evaluations show strong content accuracy and dialect results, while speaker similarity is weaker, especially for French, and multi-event paralinguistic control remains less stable.
  • The model is released under the MIT license; the page warns against non-consensual impersonation and deceptive use.

#text-to-speech #voice cloning #multilingual speech #speech synthesis

Generated by gpt-5.6-sol. Check the original for details.

Metric trends

Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained

Likes

Total likes reported by the source.

  • Hugging Face Models: 171, latest observation ; +61 over observed period since

Downloads (30d)

Rolling 30-day downloads. A change in this value is not new downloads during the observed period.

  • Hugging Face Models: 7,013, latest observation ; +4,395 over observed period since

Aliases

SourceExternal IDURL
Hugging Face ModelsinclusionAI/Ming-3.0-tts-0.5Bhttps://huggingface.co/inclusionAI/Ming-3.0-tts-0.5B Read discussion