Qualcomm® AI HubAI Hub

MeloTTS-ZH

High‑quality text‑to‑speech for Chinese.

MeloTTS is a high‑quality multi‑lingual text‑to‑speech library for English, Chinese and Spanish language.

Model RepositoryHugging FaceResearch Paper

Technical Details

Model checkpoint:myshell-ai/MeloTTS-Chinese
Max decoded sequence length:512 tokens
Number of parameters (Encoder_ZH):8.34M
Model size (Encoder_ZH) (float):31.9 MB
Number of parameters (Flow_ZH):20.1M
Model size (Flow_ZH) (float):76.9 MB
Number of parameters (Decoder_ZH):14.5M
Model size (Decoder_ZH) (float):55.5 MB
Number of parameters (BertWrapper_ZH):152M
Model size (BertWrapper_ZH) (float):581 MB

Applicable Scenarios

  • Smart Home
  • Accessibility

License

Model:MIT

Tags

  • real-time

Supported Compute Devices

  • Snapdragon X Elite CRD
  • Snapdragon X Plus 8-Core CRD
  • Snapdragon X2 Elite CRD

Supported Compute Chipsets

  • Snapdragon® X Elite
  • Snapdragon® X Plus 8-Core
  • Snapdragon® X2 Elite

Related Models

See all models
View details for the MeloTTS-EN model.

MeloTTS-EN

High-quality text-to-speech for English.

View details for the MeloTTS-ES model.

MeloTTS-ES

High-quality text-to-speech for Spanish.

View details for the Whisper-Small model.

Whisper-Small

Transformer-based automatic speech recognition (ASR) model for multilingual transcription and translation available on HuggingFace.

Looking for more? See models created by industry leaders.

Discover Model Makers