Hugging Face's logo

qualcomm
/
MeloTTS-ZH

Text-to-Audio
PyTorch
real_time
android
Model card Files
xet
 Community

MeloTTS-ZH: Optimized for Qualcomm Devices

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

This is based on the implementation of MeloTTS-ZH found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Deploying MeloTTS-ZH on-device

This model is compatible with the Qualcomm Voice AI SDK. Download the SDK from the Qualcomm Package Manager to deploy this model on-device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime Precision Chipset SDK Versions Download
VOICE_AI mixed_with_float Snapdragon® X2 Elite QAIRT 2.45 Download
VOICE_AI mixed_with_float Snapdragon® X Elite QAIRT 2.45 Download
VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® SA8775P QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® SA7255P QAIRT 2.45 Download
VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile QAIRT 2.45 Download
VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit MeloTTS-ZH on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

  • Custom weights (e.g., fine-tuned checkpoints)
  • Custom input shapes
  • Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for MeloTTS-ZH on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.audio_generation

Model Stats:

  • Max decoded sequence length: 512 tokens
  • Model checkpoint: myshell-ai/MeloTTS-Chinese
  • Model size (bert_wrapper) (float): 581 MB
  • Model size (decoder) (float): 55.5 MB
  • Model size (encoder) (float): 31.9 MB
  • Model size (flow) (float): 76.9 MB
  • Number of parameters (bert_wrapper): 152M
  • Number of parameters (decoder): 14.5M
  • Number of parameters (encoder): 8.34M
  • Number of parameters (flow): 20.1M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
bert_wrapper VOICE_AI mixed_with_float Snapdragon® X2 Elite 3.271 ms 0 - 0 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® X Elite 7.715 ms 0 - 0 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 5.128 ms 0 - 7 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 9.981 ms 0 - 3 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 30.645 ms 0 - 10 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.116 ms 0 - 1 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA8775P 9.309 ms 0 - 10 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA8650P 9.309 ms 0 - 10 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA8255P 9.309 ms 0 - 10 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 9.017 ms 0 - 2 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 7.715 ms 0 - 0 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 3.361 ms 0 - 12 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA7255P 30.645 ms 0 - 10 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 3.361 ms 0 - 12 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 2.693 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 41.107 ms 1 - 1 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® X Elite 82.927 ms 1 - 1 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 61.168 ms 2 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 74.643 ms 0 - 2 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 134.474 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 85.06 ms 0 - 2 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA8775P 83.911 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA8650P 83.911 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA8255P 83.911 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 82.761 ms 0 - 2 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 82.927 ms 1 - 1 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 48.108 ms 0 - 9 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA7255P 134.474 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 48.108 ms 0 - 9 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 42.49 ms 0 - 9 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 25.285 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® X Elite 40.439 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 30.393 ms 4 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 39.306 ms 4 - 10 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 66.6 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 40.769 ms 4 - 5 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA8775P 43.187 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA8650P 43.187 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA8255P 43.187 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 42.771 ms 4 - 9 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 40.439 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 25.433 ms 2 - 10 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA7255P 66.6 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 25.433 ms 2 - 10 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 23.812 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® X2 Elite 67.768 ms 2 - 2 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® X Elite 129.255 ms 2 - 2 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 100.215 ms 2 - 10 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 122.558 ms 2 - 6 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 245.44 ms 2 - 10 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 130.738 ms 2 - 4 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA8775P 128.57 ms 2 - 12 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA8650P 128.57 ms 2 - 12 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA8255P 128.57 ms 2 - 12 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 127.417 ms 3 - 7 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 129.255 ms 2 - 2 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 81.528 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA7255P 245.44 ms 2 - 10 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 81.528 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 71.057 ms 2 - 10 MB NPU

License

  • The license for the original implementation of MeloTTS-ZH can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Text-to-Audio
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support