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.

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® 8 Elite Gen 5 Mobile QAIRT 2.45 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® QCS8550 (Proxy) QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® SA8775P QAIRT 2.45 Download
VOICE_AI mixed_with_float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® SA7255P QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® SA8295P QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® QCS9075 QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® QCS8450 (Proxy) 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:

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 2.78 ms 0 - 10 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 3.435 ms 0 - 9 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® X2 Elite 3.329 ms 0 - 0 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® X Elite 7.38 ms 0 - 0 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® X Elite 7.38 ms 0 - 0 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 4.716 ms 0 - 7 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® QCS8275 (Proxy) 29.916 ms 0 - 8 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® QCS8550 (Proxy) 6.835 ms 0 - 2 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA8775P 9.067 ms 0 - 9 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA8775P 9.067 ms 0 - 9 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA8775P 9.067 ms 0 - 9 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® QCS9075 8.776 ms 2 - 4 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® QCS8450 (Proxy) 10.237 ms 0 - 10 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA7255P 29.916 ms 0 - 8 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA8295P 11.27 ms 0 - 6 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Elite For Galaxy Mobile 3.435 ms 0 - 9 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 42.357 ms 0 - 9 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 47.94 ms 0 - 9 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 40.252 ms 1 - 1 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® X Elite 82.762 ms 0 - 0 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® X Elite 82.762 ms 0 - 0 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 60.856 ms 0 - 7 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® QCS8275 (Proxy) 134.689 ms 0 - 9 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® QCS8550 (Proxy) 86.128 ms 0 - 2 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA8775P 83.889 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA8775P 83.889 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA8775P 83.889 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® QCS9075 83.214 ms 0 - 2 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® QCS8450 (Proxy) 114.977 ms 1 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA7255P 134.689 ms 0 - 9 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA8295P 100.031 ms 0 - 6 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite For Galaxy Mobile 47.94 ms 0 - 9 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 23.734 ms 4 - 13 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 25.575 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 25.067 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® X Elite 39.931 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® X Elite 39.931 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 30.328 ms 4 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® QCS8275 (Proxy) 66.492 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® QCS8550 (Proxy) 41.433 ms 4 - 6 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA8775P 43.224 ms 2 - 8 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA8775P 43.224 ms 2 - 8 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA8775P 43.224 ms 2 - 8 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® QCS9075 43.078 ms 6 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® QCS8450 (Proxy) 49.023 ms 4 - 13 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA7255P 66.492 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA8295P 48.396 ms 0 - 5 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite For Galaxy Mobile 25.575 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 62.516 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 78.992 ms 2 - 15 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® X2 Elite 61.707 ms 2 - 2 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® X Elite 122.569 ms 2 - 2 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® X Elite 122.569 ms 2 - 2 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 90.71 ms 2 - 9 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® QCS8275 (Proxy) 235.17 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® QCS8550 (Proxy) 123.885 ms 2 - 4 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA8775P 121.131 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA8775P 121.131 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA8775P 121.131 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® QCS9075 120.703 ms 2 - 6 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® QCS8450 (Proxy) 205.685 ms 3 - 11 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA7255P 235.17 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA8295P 150.538 ms 0 - 6 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Elite For Galaxy Mobile 78.992 ms 2 - 15 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